© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38928
    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
    åIJĦè¡Į
    -0.27
     grease
    -0.26
    åİ»è¿ĩ
    -0.26
    è¿Ļæł·åģļ
    -0.26
    itzer
    -0.25
     abused
    -0.25
    ewed
    -0.25
     gv
    -0.25
    éļľ
    -0.24
    yre
    -0.24
    POSITIVE LOGITS
    æīĵç®Ĺ
    0.30
    genesis
    0.27
     remodel
    0.26
    ernel
    0.25
     applaud
    0.25
    anship
    0.25
    alien
    0.24
    大åĶIJ
    0.24
     challeng
    0.24
    ela
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.