© 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. 20-TRANSCODER-HP
    7. 141024
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨åIJĮä¸Ģ
    -0.29
    glas
    -0.26
    >Show
    -0.25
    'an
    -0.25
     bite
    -0.25
    conomy
    -0.25
    yna
    -0.25
    imson
    -0.24
    pring
    -0.24
    åīįæĻ¯
    -0.24
    POSITIVE LOGITS
    pic
    0.29
    eph
    0.28
    igue
    0.26
    ét
    0.25
    ied
    0.25
    åī¥å¤º
    0.24
    æıŃå¼Ģ
    0.24
    avez
    0.23
    ierz
    0.23
    endez
    0.23
    Activations Density 10.527%

    No Known Activations