© 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. 8402
    Prev
    Next
    INDEX
    Explanations

    kept history

    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
    á»ģn
    -0.11
    æĢ§å¼º
    -0.09
    è½
    -0.09
    çºł
    -0.09
    _slope
    -0.09
    им
    -0.09
    å½ĵæŶçļĦ
    -0.08
    æ¯Ķèµ·
    -0.08
    çijļ
    -0.08
    åĭ¾
    -0.08
    POSITIVE LOGITS
    ä»İæľª
    0.10
    ä»İæĿ¥æ²¡æľī
    0.10
    ä»Ĭãģ¾ãģ§
    0.10
    ä»İæĿ¥
    0.10
    è®°è½½
    0.10
    å½ķ
    0.09
    çĮĿ
    0.09
    èĽĨ
    0.09
    åħļå»ºå·¥ä½ľ
    0.09
    åİĨåı²æĸ°é«ĺ
    0.09
    Activations Density 0.040%

    No Known Activations