© 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. 40127
    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
    åĬ¨äºº
    -0.29
    åľ°éģĵ
    -0.29
    ei
    -0.28
    دÙĪا
    -0.26
    èIJ½æĪ·
    -0.26
    pu
    -0.26
    èIJ¥è¿IJ
    -0.25
    å¤ļå¤ļ
    -0.25
    éĵ«
    -0.25
    ot
    -0.24
    POSITIVE LOGITS
    isode
    0.34
     Ars
    0.33
     Ins
    0.33
    å°¼æĸ¯
    0.31
    mse
    0.31
    iest
    0.31
    igos
    0.31
    resas
    0.31
    éĩĮæĸ¯
    0.31
    ãĤ¤ãĤ¹
    0.31
    Activations Density 76.428%

    No Known Activations

    This feature has no known activations.