© 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. 39855
    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
     contemporary
    -0.29
     xu
    -0.25
     interior
    -0.25
     spiritually
    -0.25
     compact
    -0.25
     Vox
    -0.24
     critical
    -0.24
     mush
    -0.23
     technical
    -0.23
     ethical
    -0.23
    POSITIVE LOGITS
    ARGV
    0.28
    åĴĮæľįåĬ¡
    0.26
    两ä½į
    0.25
     aldıģı
    0.24
    geber
    0.24
    æŃ¥éª¤
    0.24
    ackets
    0.24
    æİĽ
    0.24
    .bat
    0.24
    opc
    0.23
    Activations Density 1.366%

    No Known Activations

    This feature has no known activations.