© 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. 22-TRANSCODER-HP
    7. 130910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similar
    -0.28
    icious
    -0.27
    Similar
    -0.25
    à¹Īาà¸Ļ
    -0.25
    icense
    -0.24
    å®
    -0.24
    accept
    -0.24
     Afro
    -0.24
     Similar
    -0.24
    Reviewed
    -0.24
    POSITIVE LOGITS
    vl
    0.28
     klar
    0.26
     liar
    0.26
    çĿ¡è§ī
    0.25
    hti
    0.25
    ihilation
    0.25
     MLM
    0.25
     thinker
    0.24
     Mara
    0.24
    BOR
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.