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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44996
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    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
    .before
    -0.08
    宮
    -0.07
    ;display
    -0.06
    Scotland
    -0.06
    け
    -0.06
    Saint
    -0.06
    iage
    -0.06
     perhaps
    -0.06
    矿业
    -0.06
    ingt
    -0.06
    POSITIVE LOGITS
     courteous
    0.08
     Closure
    0.08
     efficiency
    0.07
     powstał
    0.07
    "/>.</
    0.07
     pow
    0.07
     בחי
    0.07
     Orthodox
    0.07
    zeros
    0.07
     основан
    0.07
    Activations Density 0.000%

    No Known Activations