© 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. 40460
    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
    [`
    -0.27
     regret
    -0.27
    éģĹå¿ĺ
    -0.26
    usic
    -0.25
     explicit
    -0.24
     Ñıв
    -0.24
     adamant
    -0.23
     REG
    -0.23
     prefixes
    -0.23
     regrets
    -0.23
    POSITIVE LOGITS
    ellipse
    0.25
    perfect
    0.25
    /proto
    0.25
    pline
    0.25
    bre
    0.25
    ndon
    0.24
    imiento
    0.24
    har
    0.24
    å±ħæ°ij
    0.24
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.