© 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. 23029
    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
    åĨł
    -0.26
    ilden
    -0.26
    umbnail
    -0.25
    çĻ½æĸij
    -0.25
    çİ©
    -0.24
    =Integer
    -0.24
    åĽ´ç»ķ
    -0.24
    åŀļ
    -0.23
     Gim
    -0.23
    sch
    -0.23
    POSITIVE LOGITS
    landing
    0.29
    requ
    0.28
    amel
    0.27
    è¿Ŀ
    0.27
    澤
    0.26
    amble
    0.26
    éĴĿ
    0.26
    sticky
    0.26
    arı
    0.25
    adio
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.