© 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. 98060
    Prev
    Next
    INDEX
    Explanations

    website-like text

    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
    iasm
    -0.28
     ffm
    -0.26
    utive
    -0.24
     Hutchinson
    -0.24
     churn
    -0.24
     rm
    -0.23
    uchar
    -0.23
    rium
    -0.23
    _mouse
    -0.23
    æĽ´å¤ļ
    -0.23
    POSITIVE LOGITS
    æīĢä»¥åľ¨
    0.31
    大çĽĺ
    0.26
    ç©¿
    0.26
    纷纷表示
    0.26
    ä»ĩ
    0.25
    scient
    0.24
    æĹłè®ºæĺ¯
    0.24
    Fant
    0.24
     dep
    0.24
    èĶ¸
    0.24
    Activations Density 0.001%

    No Known Activations