© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19879
    Prev
    Next
    INDEX
    Explanations

    static image or stationary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernals
    -0.10
    èĭĩ
    -0.10
    lias
    -0.10
    trys
    -0.10
    atalog
    -0.09
     ÑģебÑı
    -0.09
    .removeListener
    -0.09
    omo
    -0.09
    人次
    -0.08
    è¿«ä¸įåıĬå¾ħ
    -0.08
    POSITIVE LOGITS
    /static
    0.11
    éĿĻæĢģ
    0.10
    åijĨ
    0.10
    tics
    0.10
    .static
    0.10
     Static
    0.09
    erton
    0.09
    黣
    0.08
    _Static
    0.08
    æ¾ľ
    0.08
    Activations Density 0.122%

    No Known Activations