© 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. 130581
    Prev
    Next
    INDEX
    Explanations

    Stopwords

    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
    ((__
    -0.27
    oufl
    -0.26
    ERAL
    -0.26
    ICIAL
    -0.26
    ÏĬ
    -0.24
    SSERT
    -0.24
    frauen
    -0.23
    psy
    -0.23
    æĢ»æľī
    -0.23
    acco
    -0.23
    POSITIVE LOGITS
    ronics
    0.28
    ä¸İæѤ
    0.25
    类似
    0.24
    æĮ¥åıij
    0.24
    routing
    0.24
    intage
    0.24
    -UA
    0.23
    åIJĿ
    0.23
    缸åħ³æĸ°éĹ»
    0.23
    åį°è±¡æ·±åĪ»
    0.23
    Activations Density 8.785%

    No Known Activations