© 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. 20-TRANSCODER-HP
    7. 130817
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢĮä¸įæĺ¯
    -0.31
     rather
    -0.30
    èĢĮéĿŀ
    -0.30
    abouts
    -0.29
     plutôt
    -0.26
    å®īåħ¨ç®¡çIJĨ
    -0.26
    rather
    -0.26
    è®°å¿Ĩ
    -0.25
    apsible
    -0.25
    .LoggerFactory
    -0.24
    POSITIVE LOGITS
     prive
    0.27
    emas
    0.26
    ä¼ł
    0.26
     gang
    0.25
    _PRIV
    0.24
    _priv
    0.24
    (feature
    0.24
    uar
    0.24
     Live
    0.24
     priv
    0.23
    Activations Density 6.039%

    No Known Activations

    This feature has no known activations.