© 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. 112186
    Prev
    Next
    INDEX
    Explanations

    words

    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
    ellar
    -0.26
    æ®ĸ
    -0.25
    ë²Ī
    -0.25
    便
    -0.24
    请æķĻ
    -0.24
    ä¸īåįģå¹´
    -0.24
    åĪ¶èį¯
    -0.24
    åIJ¦
    -0.24
    äºİæĺ¯
    -0.23
    /<?
    -0.23
    POSITIVE LOGITS
    _goal
    0.25
    ioned
    0.24
    ingers
    0.24
     Friendship
    0.24
    atisf
    0.23
     setContent
    0.23
    åŁºæľ¬åİŁåĪĻ
    0.23
    ycz
    0.23
     Brill
    0.23
    à¸ģว
    0.22
    Activations Density 0.327%

    No Known Activations