© 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. 40424
    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
    驾
    -0.30
    æįķ
    -0.29
    ett
    -0.29
    ues
    -0.28
    ator
    -0.27
     Mesh
    -0.27
    ulator
    -0.27
     eth
    -0.26
     pl
    -0.25
    loc
    -0.25
    POSITIVE LOGITS
    ucha
    0.30
    conciliation
    0.27
    æ°´æĻ¶
    0.26
    '](
    0.25
    ÑĢÑİ
    0.24
    reeNode
    0.24
    ắm
    0.24
    anime
    0.24
    racial
    0.23
    ç¨İåĬ¡æĢ»å±Ģ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.