© 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. 111582
    Prev
    Next
    INDEX
    Explanations

    Dashes and to

    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
    pon
    -0.30
    Enh
    -0.28
    ACS
    -0.27
     Enh
    -0.26
     irc
    -0.25
    èµŃ
    -0.25
    ensitivity
    -0.25
    éĢįéģ¥
    -0.25
    æĿ¿
    -0.25
     Tob
    -0.25
    POSITIVE LOGITS
    ç¿Ķ
    0.27
    ä¸įéĻIJ
    0.27
    çªŁ
    0.27
    ailles
    0.26
    hani
    0.26
     ÑģовÑĢеменн
    0.25
    ä½Ĩ她
    0.25
    åħ¼é¡¾
    0.25
    ationToken
    0.25
    空åīį
    0.25
    Activations Density 0.007%

    No Known Activations