© 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. 7681
    Prev
    Next
    INDEX
    Explanations

    login and logout statuses

    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
    æ¬ł
    -0.13
    åģļåĩºäºĨ
    -0.10
    å®Ī
    -0.10
    ä¸Ģèµ·æĿ¥
    -0.09
    ething
    -0.09
    THING
    -0.09
    èIJĿåįľ
    -0.08
    INES
    -0.08
     Overs
    -0.08
    车åŃIJ
    -0.08
    POSITIVE LOGITS
    éĢIJ
    0.12
    ç»Ŀ对
    0.09
    èĩªåĬ¨
    0.09
    éļıå¤Ħåı¯è§ģ
    0.09
    lek
    0.09
    çĻ»éĻĨ
    0.08
    gil
    0.08
     Ãĸn
    0.08
     lan
    0.08
    1
    0.07
    Activations Density 0.069%

    No Known Activations