© 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. 22-TRANSCODER-HP
    7. 87138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кал
    -0.25
     constit
    -0.23
    thest
    -0.22
    èµ·æŃ¥
    -0.22
    \r
    -0.21
     Emb
    -0.21
    å¿į
    -0.21
    åİĿ
    -0.21
    urable
    -0.21
    ห
    -0.21
    POSITIVE LOGITS
    并对
    0.25
    ITTER
    0.23
     gÅĤównie
    0.23
     seperate
    0.23
     móc
    0.22
    å¹¶åľ¨
    0.22
    orc
    0.22
    eper
    0.21
    HEME
    0.21
     culo
    0.21
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.