© 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. 40426
    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
    åĨĬ
    -0.28
    ank
    -0.27
     Carpenter
    -0.26
    ä¸Ģä¸Ŀ
    -0.25
    aki
    -0.25
    emic
    -0.24
    otic
    -0.24
    %(
    -0.24
    mites
    -0.24
    who
    -0.24
    POSITIVE LOGITS
    weigh
    0.30
    apps
    0.25
     aun
    0.24
    angelo
    0.24
    dba
    0.23
    æ³ķå®ļ代表
    0.23
    rece
    0.23
    _firestore
    0.23
    æĿ¥è®²
    0.23
    schema
    0.23
    Activations Density 5.648%

    No Known Activations

    This feature has no known activations.