© 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. 40268
    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
     NOTICE
    -0.29
    GLE
    -0.27
     YT
    -0.26
     coh
    -0.25
    Dur
    -0.25
     Craig
    -0.25
     taco
    -0.23
    AKE
    -0.23
     aba
    -0.23
    计ç®ĹåĻ¨
    -0.23
    POSITIVE LOGITS
    认æ¸ħ
    0.28
    ificate
    0.26
    ä½łå¥½
    0.25
    åĵ¼
    0.25
    çŃī级
    0.25
    媸
    0.24
     Me
    0.24
    ãģĿãģ®ä»ĸ
    0.24
    使çĶ¨ç¶²è·¯
    0.24
    æĪĺ士æĿ¥è¯´
    0.23
    Activations Density 24.478%

    No Known Activations

    This feature has no known activations.