© 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. 141076
    Prev
    Next
    INDEX
    Explanations

    weather temperatures

    np_max-act · gemini-2.0-flash
    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
     replacements
    -0.27
    ä»»
    -0.27
    nia
    -0.27
    unning
    -0.25
    pread
    -0.25
    rang
    -0.24
    çľ¼
    -0.24
     PROCUREMENT
    -0.24
    isplay
    -0.24
    entre
    -0.24
    POSITIVE LOGITS
     pylint
    0.25
     capsules
    0.25
    âĬ
    0.24
    >'č↵
    0.24
    æĦŁæĥħ
    0.24
     vap
    0.24
    大éŨ
    0.24
    ắc
    0.24
    ombs
    0.24
    -authored
    0.24
    Activations Density 3.354%

    No Known Activations