© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129686
    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
     ways
    -0.27
     respects
    -0.27
     dimensions
    -0.25
    omorphic
    -0.25
     probes
    -0.25
     position
    -0.25
    ATIC
    -0.25
    åŃIJå¼Ł
    -0.25
    ways
    -0.25
     Tor
    -0.25
    POSITIVE LOGITS
    ÑĤÑģÑı
    0.31
    å¿«
    0.28
     Guinness
    0.26
    å°ıå§IJ
    0.25
    æijĦ
    0.25
    ç¥ķ
    0.24
    iana
    0.24
    Experts
    0.24
     :-↵
    0.23
    社
    0.23
    Activations Density 6.243%

    No Known Activations

    This feature has no known activations.