© 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. 33-TRANSCODER-HP
    7. 54529
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amac
    -0.31
    Mixed
    -0.27
     Mixed
    -0.27
    `\
    -0.25
    éļĽ
    -0.24
    BS
    -0.24
     Verm
    -0.24
     dạng
    -0.24
    anova
    -0.23
     Reason
    -0.23
    POSITIVE LOGITS
    åģļå®Į
    0.27
    .GroupLayout
    0.25
     here
    0.24
    å¦Ĥæŀľæ²¡æľī
    0.24
    çĺ¿
    0.24
    åĸľ
    0.24
    UBL
    0.24
    åĢĻéĢī
    0.24
     visiting
    0.23
     mutually
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.