© 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. 23162
    Prev
    Next
    INDEX
    Explanations

    code or languages

    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
     Focus
    -0.30
    agon
    -0.28
    Focus
    -0.28
    -focus
    -0.27
     plot
    -0.27
    åĬ¡
    -0.27
    çĽĸ
    -0.26
    .EventHandler
    -0.26
    çĽij
    -0.26
    ;c
    -0.25
    POSITIVE LOGITS
     owe
    0.29
     owes
    0.27
     redeemed
    0.27
    齿
    0.26
    ixa
    0.26
    _reserved
    0.25
    prites
    0.24
    âĩij
    0.24
    æ©Ľ
    0.24
    css
    0.24
    Activations Density 0.002%

    No Known Activations