© 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. 27687
    Prev
    Next
    INDEX
    Explanations

    legal violation affects persons

    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
    ç¹ģå¿Ļ
    -0.10
    olas
    -0.09
    aper
    -0.09
    ichel
    -0.09
    çĽ´è¾¾
    -0.09
    妾
    -0.08
    inea
    -0.08
    uckland
    -0.08
    é¡¿
    -0.08
     Mine
    -0.08
    POSITIVE LOGITS
    å¯ĨåĪĩåħ³æ³¨
    0.09
    æĶ¶ç¼©
    0.08
    æĤĦæĤĦ
    0.08
    StateException
    0.08
    asad
    0.08
    оде
    0.08
    bie
    0.08
    æĢ¥åī§
    0.08
    èĤª
    0.08
    éĻ¶
    0.08
    Activations Density 0.004%

    No Known Activations