© 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. 23333
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iale
    -0.28
    кÑģ
    -0.27
    æ¨ĺ
    -0.27
    icamente
    -0.26
    Ãły
    -0.25
    iere
    -0.25
    naments
    -0.25
    reeting
    -0.24
    æ±Ń
    -0.24
     dél
    -0.24
    POSITIVE LOGITS
    åĽ¤
    0.26
    被æĬĵ
    0.26
     assaulted
    0.25
    积èĵĦ
    0.25
    successful
    0.24
    åı¯æݧ
    0.24
    æľīè¿ĩ
    0.24
    羣çļĦæĺ¯
    0.24
    itos
    0.24
    .methods
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.