© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    police officers and staff

    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
    æµģæĺŁ
    -0.10
    äºĴè¡¥
    -0.09
    被人
    -0.09
    åijĬè¯īæĪij
    -0.09
    nts
    -0.09
    æĦŁãģĺ
    -0.09
    åij»
    -0.09
    ÙĦØ©
    -0.08
    ç»ı纬
    -0.08
    _Impl
    -0.08
    POSITIVE LOGITS
     nic
    0.11
    aru
    0.09
    åĪ°æĿ¥
    0.09
    ä¸Ģè¡Į
    0.09
    ounce
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    举åĬŀçļĦ
    0.08
    æīĵ交éģĵ
    0.08
    æıIJåĩºçļĦ
    0.08
    çĶļ
    0.08
    Activations Density 0.152%

    No Known Activations