© 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. 23-TRANSCODER-HP
    7. 25230
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ++↵
    -0.29
    ittel
    -0.28
    ersed
    -0.27
    soles
    -0.27
    aday
    -0.27
    çĨŁ
    -0.27
    reet
    -0.25
    alité
    -0.25
    ä¸ĢåIJ¬
    -0.25
    sworth
    -0.24
    POSITIVE LOGITS
     Stevens
    0.27
    åľ¨è¿Ļæĸ¹éĿ¢
    0.27
    .decorators
    0.25
    _clr
    0.25
    cente
    0.25
    TRA
    0.24
     Schro
    0.24
     Log
    0.24
     True
    0.23
    -cn
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.