© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clown
    -0.28
    æ¸ħæī«
    -0.26
    åĿĩè¡¡
    -0.26
     Clara
    -0.26
     doubts
    -0.25
    .about
    -0.25
     amb
    -0.24
     gmail
    -0.24
     Airbnb
    -0.24
    enade
    -0.24
    POSITIVE LOGITS
     BaÅŁ
    0.29
    轨迹
    0.29
    odia
    0.27
    akis
    0.26
    orean
    0.25
     мед
    0.25
    opot
    0.25
    æ´Ľ
    0.24
     bas
    0.24
    -mask
    0.24
    Activations Density 0.964%

    No Known Activations