© 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. 97697
    Prev
    Next
    INDEX
    Explanations

    computer/technical language

    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
    æīİ
    -0.32
     Tune
    -0.28
    æİ¥è¿ij
    -0.27
     close
    -0.26
     clen
    -0.25
     forthcoming
    -0.25
    filt
    -0.25
    .tail
    -0.24
     facing
    -0.24
     Close
    -0.24
    POSITIVE LOGITS
    ipers
    0.27
    å¾Īæ£Ĵ
    0.26
    usercontent
    0.26
    acs
    0.25
    æĬľ
    0.25
    acket
    0.24
    MainFrame
    0.23
    æĥĬ人
    0.23
     balk
    0.23
    orns
    0.23
    Activations Density 0.001%

    No Known Activations