© 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. 141828
    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
    èĦļä¸ĭ
    -0.27
    èĽĭçĻ½
    -0.25
    éĺĥ
    -0.25
     CrossRef
    -0.25
    ssi
    -0.25
    ariat
    -0.25
    éĤĪ
    -0.24
    ä¿İ
    -0.24
     Consort
    -0.24
    åĬ¡å·¥
    -0.24
    POSITIVE LOGITS
     applyMiddleware
    0.28
    æĻĭ
    0.27
    ieg
    0.27
    æł·
    0.27
    æ¹
    0.26
    åĩij
    0.25
    chip
    0.25
    è¿ĩé«ĺ
    0.25
    midd
    0.25
    æĵį
    0.24
    Activations Density 26.819%

    No Known Activations

    This feature has no known activations.