© 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. 22-TRANSCODER-HP
    7. 112027
    Prev
    Next
    INDEX
    Explanations

    only/just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aul
    -0.28
     stead
    -0.27
     Hot
    -0.27
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.27
    _term
    -0.26
    .heap
    -0.26
    æĽ´å¤ļ
    -0.26
    éļIJ约
    -0.25
    term
    -0.25
    สว
    -0.25
    POSITIVE LOGITS
    ittance
    0.32
    عÙĬ
    0.29
    mys
    0.28
    /false
    0.27
     communic
    0.26
    å¤ĸ交éĥ¨
    0.26
    -strip
    0.24
     essentials
    0.24
     beim
    0.24
    comic
    0.24
    Activations Density 0.017%

    No Known Activations