© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 2594
    Prev
    Next
    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash

    phrases that express a speaker’s stance or emphasis, such as hedges, certainty qualifiers, and intensifiers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bev
    -0.07
    のご
    -0.07
     interv
    -0.07
     דרכים
    -0.06
     då
    -0.06
    두
    -0.06
    笔试
    -0.06
    .Priority
    -0.06
    maps
    -0.06
    -tr
    -0.06
    POSITIVE LOGITS
     Basically
    0.07
    (cancel
    0.07
    UE
    0.07
    而导致
    0.07
    (ed
    0.06
    typing
    0.06
    .effect
    0.06
    precated
    0.06
    masına
    0.06
    unge
    0.06
    Activations Density 0.315%

    No Known Activations