© 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. 112795
    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
    Stretch
    -0.27
    追
    -0.27
    tsy
    -0.25
    a
    -0.25
    OUS
    -0.25
    endars
    -0.25
    åľī
    -0.24
    gles
    -0.24
    apeutic
    -0.24
    ç©
    -0.24
    POSITIVE LOGITS
    upgrade
    0.26
    ycopg
    0.26
    _based
    0.24
    ä¹Ĵä¹ĵ
    0.24
    ylene
    0.24
    çļĦæĦıæĢĿ
    0.24
    fusion
    0.24
    bbing
    0.23
    _DECL
    0.23
    .tp
    0.23
    Activations Density 0.077%

    No Known Activations

    This feature has no known activations.