© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    button actions

    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
    OTO
    -0.09
    åŃ½
    -0.09
    å®ĮåĸĦ
    -0.09
    rug
    -0.09
    åĩºå¤Ħ
    -0.08
    缴éĢļ车
    -0.08
    èŁĭ
    -0.08
     fruition
    -0.08
    çļĦæķ´ä½ĵ
    -0.08
    å¤ĦåĪĨ
    -0.08
    POSITIVE LOGITS
    ä¸ī家
    0.10
    æĬĢå·§
    0.09
    两家
    0.09
    ä½łè§īå¾Ĺ
    0.09
    oce
    0.09
    åİĭ
    0.08
    å·§
    0.08
    ä¼ļè®©ä½ł
    0.08
    åĩłå®¶
    0.08
    aul
    0.08
    Activations Density 0.034%

    No Known Activations