© 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. 7652
    Prev
    Next
    INDEX
    Explanations

    safety, protection, surveillance, alarm

    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
    reff
    -0.12
    /downloads
    -0.09
    رÙĪÙĨ
    -0.09
    cul
    -0.09
    re
    -0.09
    饿
    -0.09
     má»Ļ
    -0.08
    åĢĴåľ¨
    -0.08
    æģ³
    -0.08
    笳
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¼ł
    0.08
    大å®Ĺ
    0.08
    çĥŃ带
    0.08
    ophobic
    0.08
    ë§
    0.08
    orth
    0.08
     mos
    0.08
    éĺ
    0.08
    è°±
    0.08
    idget
    0.08
    Activations Density 0.011%

    No Known Activations