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

    Neuronpedia

    Jacobian LensNEW
    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. 121870
    Prev
    Next
    INDEX
    Explanations

    Holding something back

    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
    .voice
    -0.07
    arch
    -0.07
    רגש
    -0.07
     kond
    -0.07
     profess
    -0.07
    seudo
    -0.07
    -font
    -0.07
    ([^
    -0.07
    .round
    -0.07
     זוכר
    -0.07
    POSITIVE LOGITS
    ERTICAL
    0.07
    ハー
    0.07
    >.</
    0.07
     */,↵
    0.07
    反腐倡
    0.06
    嚓
    0.06
    "})
    0.06
    "}),↵
    0.06
    '})
    0.06
    ."),↵
    0.06
    Activations Density 0.003%

    No Known Activations