© 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. 31-TRANSCODER-HP
    7. 18956
    Prev
    Next
    INDEX
    Explanations

    negative incidents or outcomes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uty
    -0.29
     agre
    -0.27
    NSE
    -0.25
    òng
    -0.24
    itational
    -0.24
     Äijè
    -0.24
    -temp
    -0.24
    çĭ¬è§Ĵ
    -0.24
    lands
    -0.23
    AAF
    -0.23
    POSITIVE LOGITS
    throw
    0.30
    丢
    0.29
    æİī
    0.29
    adel
    0.28
    æĬĽ
    0.28
     throw
    0.27
    è·ij
    0.27
     throwing
    0.26
     shed
    0.26
    丣
    0.26
    Activations Density 0.091%

    No Known Activations