© 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. 129676
    Prev
    Next
    INDEX
    Explanations

    Technical/Informational text excerpts

    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
     hacked
    -0.26
    æīįè¡Į
    -0.25
    -caret
    -0.25
    æĦıæĥ³ä¸įåĪ°
    -0.25
    bucks
    -0.24
    æīĵçĿĢ
    -0.24
    poons
    -0.24
    æĤ
    -0.23
    ä¸įè´Ł
    -0.23
    æłĭ
    -0.23
    POSITIVE LOGITS
    rtype
    0.26
     Ballard
    0.26
    iÅŁ
    0.26
    éģ¿ãģij
    0.26
    aiser
    0.25
    zte
    0.24
    undy
    0.24
    ibr
    0.24
     vazgeç
    0.23
     included
    0.23
    Activations Density 0.011%

    No Known Activations