© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57463
    Prev
    Next
    INDEX
    Explanations

    Getty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĦÑĤ
    -0.26
     chops
    -0.25
     circ
    -0.25
     pap
    -0.25
    fol
    -0.25
    fst
    -0.25
     foll
    -0.25
    rette
    -0.24
     early
    -0.24
    "h
    -0.24
    POSITIVE LOGITS
    pagination
    0.25
    skirts
    0.25
    é£İæľº
    0.25
    <TextView
    0.24
     Æ°u
    0.24
    Statics
    0.24
    è¿ĽåĨĽ
    0.24
    quarters
    0.24
    quarter
    0.23
    åĴ¨è¯¢æľįåĬ¡
    0.23
    Activations Density 0.012%

    No Known Activations