© 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. 43170
    Prev
    Next
    INDEX
    Explanations

    Network protocols and security

    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
     tk
    -0.25
    .Acc
    -0.25
     subsidi
    -0.25
     Knock
    -0.24
    å·¥åħ·
    -0.24
    lest
    -0.24
    TK
    -0.24
    tk
    -0.23
    subs
    -0.23
    Calls
    -0.23
    POSITIVE LOGITS
     SR
    0.40
    SR
    0.36
    _SR
    0.33
    SD
    0.30
    uese
    0.29
     Sr
    0.27
    DT
    0.27
     DT
    0.27
     SD
    0.27
    ST
    0.27
    Activations Density 0.029%

    No Known Activations