© 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. 30900
    Prev
    Next
    INDEX
    Explanations

    vulgar insults

    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
    OLE
    -0.10
     mole
    -0.09
    èĦļ
    -0.09
    åĴĴ
    -0.09
    èĩªå®¶
    -0.09
    atte
    -0.09
    鹪
    -0.09
    irsch
    -0.09
     enjo
    -0.09
    ç²¾
    -0.09
    POSITIVE LOGITS
    BALL
    0.08
    家ä¼Ļ
    0.08
    ÑĢÑĥÑĤ
    0.08
    è¾Ī
    0.07
    etro
    0.07
    etros
    0.07
    ç¿Ł
    0.07
     dru
    0.07
    beck
    0.07
    éļıå¤Ħ
    0.07
    Activations Density 0.002%

    No Known Activations