© 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. 22572
    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
     Disclaimer
    -0.27
    mÃ¤ÃŁig
    -0.26
    绾
    -0.26
    çļĦè¯Ŀ
    -0.25
     vern
    -0.25
    iates
    -0.25
    SENS
    -0.25
    ymm
    -0.24
    iating
    -0.24
    ante
    -0.24
    POSITIVE LOGITS
    åĩłæŃ¥
    0.30
    pis
    0.28
    (js
    0.26
    沤
    0.26
    éĩĬ
    0.26
    çļ±
    0.26
    Mocks
    0.25
    /js
    0.25
     UIS
    0.25
    .jsoup
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.