© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9088
    Prev
    Next
    INDEX
    Explanations

    names starting with iche, Domin, Gab, Fab, Jo, step

    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
    getc
    -0.09
    å·´æĸ¯
    -0.08
     Walters
    -0.08
    èĢģåŃIJ
    -0.08
    å¼Ģåħĥ
    -0.08
    æīĺ管
    -0.08
    обÑĭ
    -0.08
    -gap
    -0.07
    ecz
    -0.07
     Nicholson
    -0.07
    POSITIVE LOGITS
    иде
    0.10
    pig
    0.09
    åįĸ家
    0.09
    æĶĢ
    0.09
    ç»ıçIJĨ
    0.09
    æ½ľ
    0.08
    轶
    0.08
    leigh
    0.08
    çĸĹç¨ĭ
    0.08
     Verm
    0.08
    Activations Density 0.464%

    No Known Activations