© 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. 12-TRANSCODER-HP
    7. 23588
    Prev
    Next
    INDEX
    Explanations

    engulf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺĻ
    -0.29
    æݨ广
    -0.29
     Forums
    -0.28
    Formation
    -0.26
     Promotion
    -0.26
    Premium
    -0.25
     Commentary
    -0.25
    yne
    -0.25
    精彩
    -0.25
     promotional
    -0.24
    POSITIVE LOGITS
     range
    0.31
    åı£è¢ĭ
    0.30
    æłĸ
    0.29
    range
    0.27
    ranges
    0.26
     destiny
    0.26
     ranging
    0.25
    sted
    0.25
     shim
    0.25
     RANGE
    0.24
    Activations Density 0.001%

    No Known Activations