© 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. 22655
    Prev
    Next
    INDEX
    Explanations

    in the range

    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
    èĻ¹
    -0.10
    å°½åı¯èĥ½
    -0.10
    帮ä»ĸ
    -0.10
    åī¯éĻ¢éķ¿
    -0.10
    imd
    -0.09
    åĬ©çIJĨ
    -0.09
    çľ¼éĩĮ
    -0.08
    èĥ½çľĭåĪ°
    -0.08
    çļĦçľ¼
    -0.08
    çģ¯ç¬¼
    -0.08
    POSITIVE LOGITS
    æģ¶åĬ£
    0.11
    éģĩ
    0.11
    éķ¿éĢĶ
    0.10
    éģĩåĪ°
    0.10
    éĹ®é¢ĺæĺ¯
    0.10
    éģĩè§ģ
    0.09
    è¾ĥéķ¿
    0.09
    éķ¿æŶéĹ´
    0.09
    éļĽ
    0.09
    çݯå¢ĥ
    0.09
    Activations Density 0.239%

    No Known Activations