© 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. 23-RESID-POST-AA
    11. 604
    Prev
    Next
    INDEX
    Explanations

    say "control"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyến
    -0.08
    entities
    -0.07
     بالن
    -0.07
     enticing
    -0.07
     تحت
    -0.06
    _piece
    -0.06
     concaten
    -0.06
    -0.06
    одерж
    -0.06
    二氧化碳
    -0.06
    POSITIVE LOGITS
     jars
    0.07
     octave
    0.07
     Juda
    0.07
    ᡤ
    0.07
    _fold
    0.07
    :System
    0.06
     Dy
    0.06
    svm
    0.06
     Laur
    0.06
    _Util
    0.06
    Activations Density 0.395%

    No Known Activations