© 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. 107500
    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
    好åIJĥ
    -0.27
     competency
    -0.26
    AFF
    -0.26
    è°Ĭ
    -0.25
    ulp
    -0.24
    IJľ
    -0.24
    _aff
    -0.23
    ienen
    -0.23
    imonials
    -0.23
    ctp
    -0.23
    POSITIVE LOGITS
    ugen
    0.29
    ogn
    0.28
    ]")]↵
    0.27
    åįİ
    0.27
     muse
    0.27
    ä¸Ĭåīį
    0.27
    çĽ¾
    0.25
    ]]↵↵
    0.25
    彩
    0.24
    æĸľ
    0.24
    Activations Density 1.119%

    No Known Activations

    This feature has no known activations.