© 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. 39540
    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
    æĪ¿ä¸ľ
    -0.27
    å¤Ħåľ¨
    -0.25
    æ¯ıä½į
    -0.25
    iert
    -0.25
     mascot
    -0.25
    ä¸įåıĺ
    -0.24
    ","","
    -0.24
    æ½ľåľ¨
    -0.24
    ;\↵
    -0.23
    Opening
    -0.23
    POSITIVE LOGITS
    ä¸įè¦ģ太
    0.29
     Wass
    0.26
    plex
    0.26
    WA
    0.26
    -index
    0.25
    è¿ĩå¾Ĺ
    0.25
    WAR
    0.24
    ward
    0.24
    äºĨæĪijçļĦ
    0.24
    news
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.