© 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. 12-TRANSCODER-HP
    7. 23074
    Prev
    Next
    INDEX
    Explanations

    scientific papers related to genetics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uggy
    -0.27
     distinguished
    -0.26
    expected
    -0.26
     expected
    -0.26
     tenant
    -0.25
    客åķĨ
    -0.25
     symmetric
    -0.25
    .Axis
    -0.24
     TEN
    -0.24
    [axis
    -0.23
    POSITIVE LOGITS
    ion
    0.28
    illion
    0.25
    'im
    0.25
     IRA
    0.24
    家åĬ¡
    0.24
    å¹³åĿĩæ¯ı
    0.24
    åľ¨é¦Ļ港
    0.24
    æĹı
    0.23
    亲
    0.23
    ä¸įçĶ±
    0.23
    Activations Density 0.001%

    No Known Activations