© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56562
    Prev
    Next
    INDEX
    Explanations

    security and vulnerability

    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
    æĮ¡
    -0.11
    çķ´
    -0.09
    isk
    -0.09
    adge
    -0.09
    æİī
    -0.09
    è§ī
    -0.09
    é£İå°ļ
    -0.09
    çŃī级
    -0.09
     yarg
    -0.08
    æ¡£
    -0.08
    POSITIVE LOGITS
    çĶ³
    0.11
    åłĨ积
    0.09
    溢
    0.09
     wast
    0.09
    _nth
    0.09
    ä¸Ģ大åłĨ
    0.08
    åªĴä»ĭ
    0.08
    æįIJçĮ®
    0.08
    人éĢł
    0.08
    çĶ³è´Ń
    0.08
    Activations Density 0.162%

    No Known Activations