© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36493
    Prev
    Next
    INDEX
    Explanations

    past studies, position, medal

    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
    abet
    -0.11
    æĺ¯ä¸įåı¯èĥ½
    -0.11
    åħĪè¿ĽçļĦ
    -0.10
    entlich
    -0.09
    ç»Ī身
    -0.09
    人å¿ĥ
    -0.09
    åīį沿
    -0.09
    ÙĤع
    -0.09
    ç»ĪçĶŁ
    -0.09
    ï¸
    -0.09
    POSITIVE LOGITS
    çĻ¾å®¶
    0.09
    slash
    0.09
    åIJĦ家
    0.09
    ype
    0.08
    Past
    0.08
    iche
    0.08
     past
    0.08
    åĽ
    0.08
    reich
    0.08
     Past
    0.08
    Activations Density 0.025%

    No Known Activations