© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130872
    Prev
    Next
    INDEX
    Explanations

    Computer code and technical writing

    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
    summ
    -0.28
    tor
    -0.27
    ritable
    -0.27
    OOM
    -0.26
    åĵ¥ä¼¦
    -0.26
    éĺ³åİ¿
    -0.25
    apan
    -0.25
    ä¸įå±ŀäºİ
    -0.24
    cem
    -0.24
    积èĵĦ
    -0.24
    POSITIVE LOGITS
    èijĹ
    0.29
    çĿĢ
    0.25
     Overse
    0.25
     Printf
    0.24
    éģĩ
    0.23
    -notes
    0.23
     INTERNATIONAL
    0.23
    ILED
    0.23
    ī
    0.23
    REW
    0.23
    Activations Density 0.014%

    No Known Activations