© 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. 11-RESID-POST-AA
    11. 85188
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    questions or requests for advice/help (utterances beginning with question words like what/how/do).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expectation
    -0.07
     недел
    -0.07
    TestId
    -0.07
     swims
    -0.06
    𫶇
    -0.06
    +z
    -0.06
    낱
    -0.06
    <Void
    -0.06
     debtor
    -0.06
    Requires
    -0.06
    POSITIVE LOGITS
    明确
    0.08
    bas
    0.07
    efficient
    0.07
    ง
    0.07
    Types
    0.07
    婴
    0.07
     населения
    0.07
    aments
    0.07
     arbe
    0.07
    У
    0.07
    Activations Density 0.095%

    No Known Activations