© 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. 35-TRANSCODER-HP
    7. 39992
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .webkit
    -0.29
    PEC
    -0.24
    ''
    -0.24
    æĶ»
    -0.24
    æ·¬
    -0.24
    çªģçł´åı£
    -0.24
    éļĪ
    -0.24
    åĨ¬åŃ£
    -0.23
    å·¥åľ°
    -0.23
    æĦį
    -0.23
    POSITIVE LOGITS
    umb
    0.33
    UMB
    0.30
    folio
    0.30
    solete
    0.27
    çŀ»
    0.26
    èŀºæĹĭ
    0.25
    >Type
    0.25
     depreci
    0.24
     err
    0.23
     dil
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.