© 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. 42136
    Prev
    Next
    INDEX
    Explanations

    sympath

    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
    gett
    -0.32
    .getTag
    -0.27
     bat
    -0.26
    ante
    -0.25
    qus
    -0.25
    atan
    -0.25
    leitung
    -0.25
     irre
    -0.24
    åħ¶å®ĥéĹ®é¢ĺ
    -0.24
     comb
    -0.24
    POSITIVE LOGITS
    icide
    0.30
    eni
    0.28
     ary
    0.28
    takes
    0.27
     takes
    0.27
    åĩºçĤī
    0.27
     Lynch
    0.27
    -IS
    0.26
    åIJķ
    0.26
    Taking
    0.26
    Activations Density 0.002%

    No Known Activations