© 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. 130805
    Prev
    Next
    INDEX
    Explanations

    IC

    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
     massages
    -0.24
    UNT
    -0.23
    uary
    -0.23
    panion
    -0.23
    bach
    -0.23
    rosse
    -0.23
    ç¥ŀç§ĺ
    -0.22
    åIJĥ饱
    -0.22
    otec
    -0.22
    _pref
    -0.22
    POSITIVE LOGITS
    æѤåīį
    0.27
    &R
    0.24
    les
    0.24
    è¿Ļæľ¬ä¹¦
    0.23
    æŃ£å¸¸çļĦ
    0.23
    è¿Ļä¸Ģ
    0.23
    than
    0.23
    ĻĤ
    0.23
    pis
    0.22
     vill
    0.22
    Activations Density 0.004%

    No Known Activations