© 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. 22-TRANSCODER-HP
    7. 87660
    Prev
    Next
    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _gs
    -0.33
    quarters
    -0.28
    |i
    -0.27
    Gas
    -0.26
    çľ¼çľĭ
    -0.25
    æĬĽ
    -0.25
     Levy
    -0.24
    iesz
    -0.24
    å®ŀè·µä¸Ń
    -0.24
    opot
    -0.24
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.26
    &_
    0.25
    cycl
    0.25
    .*,
    0.24
     ÅŁeyler
    0.24
    'autres
    0.23
    ä»Ģä¹Īåij¢
    0.23
    oyal
    0.23
    åĴĮä»ĸçļĦ
    0.23
    rette
    0.23
    Activations Density 0.055%

    No Known Activations