© 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. 43339
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    æ¹ĸåĮº
    -0.28
    ãĤŃãĥ£ãĥ³
    -0.26
    ONA
    -0.26
    åħļé£İ
    -0.25
    =[↵
    -0.24
    ))-
    -0.24
    åİ¿åŁİ
    -0.24
    лаг
    -0.23
    èµŀèµı
    -0.23
    纨
    -0.23
    POSITIVE LOGITS
     {
    0.65
    {
    0.63
    {-
    0.51
    {"
    0.50
    {'
    0.50
     {-
    0.49
    {n
    0.47
    {T
    0.46
    {|
    0.45
    {s
    0.45
    Activations Density 0.053%

    No Known Activations