© 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. 39194
    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
    mue
    -0.28
    otron
    -0.26
    ERRU
    -0.26
     paste
    -0.25
    çĶŁçī©ç§ijæĬĢ
    -0.25
     sche
    -0.24
    ewear
    -0.24
    schlä
    -0.24
     inset
    -0.24
     msm
    -0.24
    POSITIVE LOGITS
    lob
    0.28
    é¹Ħ
    0.27
    åij½è¿IJ
    0.26
    å¼Ī
    0.25
    DN
    0.24
    min
    0.24
    ç«Łæĺ¯
    0.24
    顶
    0.24
    æŃ¥è¡Į
    0.24
     DN
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.