© 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. 30051
    Prev
    Next
    INDEX
    Explanations

    housewives and wife

    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
    管å±Ģ
    -0.09
    æīĪ
    -0.09
    éºĵ
    -0.09
    MMdd
    -0.08
    人身
    -0.08
    ลà¸ļ
    -0.08
    odable
    -0.08
    Som
    -0.08
     Som
    -0.08
    满äºĨ
    -0.08
    POSITIVE LOGITS
    çŃIJ
    0.10
    ä¸įåłª
    0.08
    CHAT
    0.08
    èĢģåħ¬
    0.08
    éĶ»
    0.08
    åĶ¯
    0.08
    еÑģÑĤв
    0.08
    kur
    0.08
    èĢĮåıĪ
    0.08
    åľ¨å½ĵåľ°
    0.08
    Activations Density 0.003%

    No Known Activations