© 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. 88093
    Prev
    Next
    INDEX
    Explanations

    depending

    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
    弧
    -0.24
    çį¨
    -0.23
    à´ª
    -0.23
    çĭ¬
    -0.23
    idia
    -0.23
    åĩºå¢ĥ
    -0.23
    æİ¥å¾ħ
    -0.23
    ONUS
    -0.23
    apor
    -0.22
    íĬ¹ë³Ħ
    -0.22
    POSITIVE LOGITS
    habi
    0.28
    纳æĸ¯
    0.28
    ynos
    0.27
    çļĦç»ıéªĮ
    0.26
    male
    0.26
    ä¸Ģé¢Ĺ
    0.24
    大佬
    0.24
    vers
    0.24
    çļĦ巨大
    0.23
    åıį转
    0.23
    Activations Density 0.840%

    No Known Activations