© 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. 19834
    Prev
    Next
    INDEX
    Explanations

    security and secure contexts

    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
     Bras
    -0.09
    chos
    -0.09
    æ¯ĴæĢ§
    -0.08
    pta
    -0.08
    elin
    -0.08
    形容
    -0.08
    çªĦ
    -0.08
    çŁ¥æĻĵ
    -0.08
     Trev
    -0.08
    á»ģn
    -0.08
    POSITIVE LOGITS
    _CLOSED
    0.09
    åŁºåĩĨ
    0.08
    åĢŁè´·
    0.08
    漩
    0.08
    ç°
    0.08
    /sc
    0.08
    çĥĻ
    0.08
    æ§Į
    0.08
    åIJĥåĪ°
    0.08
    æĤį
    0.08
    Activations Density 0.072%

    No Known Activations