© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43987
    Prev
    Next
    INDEX
    Explanations

    Math/formulas

    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
    Negative Logits
     /**č↵
    -0.32
    =[↵
    -0.31
     /**↵
    -0.30
    姹
    -0.30
    /**č↵
    -0.28
    ])-
    -0.27
    ))-
    -0.26
    =#{
    -0.26
    /**↵
    -0.25
    åħļé£İ
    -0.25
    POSITIVE LOGITS
     {
    0.76
    {
    0.73
    {n
    0.58
    {k
    0.57
    {s
    0.55
    {T
    0.54
    {(
    0.54
    {i
    0.54
    {x
    0.52
    {id
    0.52
    Activations Density 0.056%

    No Known Activations