© 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. 32-TRANSCODER-HP
    7. 41719
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     land
    -0.40
     outdoor
    -0.40
     outdoors
    -0.34
    室å¤ĸ
    -0.33
    åľŁåľ°
    -0.31
    Outdoor
    -0.30
    outs
    -0.30
     Outdoor
    -0.29
    Land
    -0.29
     LAND
    -0.29
    POSITIVE LOGITS
    çıŃ
    0.26
    acob
    0.26
     tagName
    0.24
    rong
    0.23
    geme
    0.23
    Zip
    0.23
    æī¹åıijå¸Ĥåľº
    0.23
    èĵ¬åĭĥ
    0.23
    upal
    0.23
    logan
    0.23
    Activations Density 0.003%

    No Known Activations