© 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. 97435
    Prev
    Next
    INDEX
    Explanations

    Technical/Garbled data

    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
    ä¹Łä¸įæĥ³
    -0.33
    é¹ľ
    -0.28
    èĢĮåİ»
    -0.28
    ием
    -0.28
    ç½¢
    -0.27
    cem
    -0.27
    æĹģ
    -0.26
    xBE
    -0.26
    éķŀ
    -0.26
    å¾Ģå¤ĸ
    -0.25
    POSITIVE LOGITS
    ory
    0.29
    ery
    0.27
    acy
    0.27
     Holt
    0.26
    iry
    0.25
    irts
    0.25
     reg
    0.24
    '])[
    0.24
     hiding
    0.24
    fm
    0.23
    Activations Density 0.004%

    No Known Activations