© 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. 43461
    Prev
    Next
    INDEX
    Explanations

    the

    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
    é¢Ĩ导
    -0.26
    .wikipedia
    -0.26
     BX
    -0.25
     Manuals
    -0.25
    lli
    -0.25
    éļı
    -0.24
    ipl
    -0.24
    zl
    -0.24
     acting
    -0.24
    Endpoint
    -0.24
    POSITIVE LOGITS
    season
    0.26
    æ¤įæłij
    0.25
     contested
    0.25
    å¿ĥè·³
    0.25
     Align
    0.24
    æĸĹå¿Ĺ
    0.24
    \widgets
    0.24
    uter
    0.24
    anke
    0.24
    sep
    0.23
    Activations Density 0.000%

    No Known Activations