© 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. 87254
    Prev
    Next
    INDEX
    Explanations

    week or month

    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
    iola
    -0.30
    pite
    -0.30
    uba
    -0.29
    äºĴ
    -0.29
    abin
    -0.28
     enfrent
    -0.28
    annis
    -0.26
     Pep
    -0.26
    åįıè°ĥ
    -0.25
    åİŁæľī
    -0.25
    POSITIVE LOGITS
    åĴ±ä»¬
    0.29
    æĪij们
    0.29
    æĤ¨
    0.29
    为æĤ¨
    0.29
    éĢıè¿ĩ
    0.27
    ç»ĻæĤ¨
    0.27
     award
    0.26
    åĴ±
    0.26
    æĤ¨çļĦåŃ©åŃIJ
    0.25
    æĤ¨çļĦ
    0.25
    Activations Density 0.009%

    No Known Activations