© 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. 33609
    Prev
    Next
    INDEX
    Explanations

    medical treatments and injuries

    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
    åłµ
    -0.10
    éĵ¯
    -0.10
    èĪ
    -0.10
    åħ¼
    -0.10
    åīĸ
    -0.09
    æ´Ĺå¹²åĩĢ
    -0.09
     liá»ĩt
    -0.09
    èĵ¦
    -0.09
    å¾Ĺä¸įåĪ°
    -0.09
    å¹²åĩĢ
    -0.09
    POSITIVE LOGITS
    åľĥ
    0.10
    轻微
    0.10
    åĺ´
    0.09
    æĴµ
    0.08
     forg
    0.08
     Sp
    0.08
    èĥ¸
    0.08
    rac
    0.08
    èĩªæľī
    0.08
    ç¾İæľ¯
    0.08
    Activations Density 0.027%

    No Known Activations