© 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. 25-TRANSCODER-HP
    7. 109255
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĢеÑĪа
    -0.28
    IJľç´¢
    -0.27
    iques
    -0.25
     SOAP
    -0.25
    IJľ
    -0.25
    ervised
    -0.25
    ä¸įçĶ¨
    -0.24
    .echo
    -0.24
    _wc
    -0.24
    gradable
    -0.23
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.28
     kre
    0.28
     catch
    0.27
    kh
    0.27
    AuthGuard
    0.26
    kre
    0.26
    æľīçĶ¨
    0.26
    .Creator
    0.26
     decoration
    0.24
    DOC
    0.24
    Activations Density 1.342%

    No Known Activations

    This feature has no known activations.