© 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. 36238
    Prev
    Next
    INDEX
    Explanations

    neurological conditions and symptoms

    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
    宵
    -0.09
    åĵ¨
    -0.09
    笳
    -0.09
     hÆ°
    -0.09
     Uns
    -0.08
    (net
    -0.08
    ogue
    -0.08
    ä¸įæŃ»
    -0.08
    åĬŀåħ¬åİħ
    -0.08
    åIJİåį«
    -0.08
    POSITIVE LOGITS
    è¬ĩ
    0.10
    丧失
    0.10
    æľºèĥ½
    0.09
    èĥ½åĬĽ
    0.09
    KP
    0.09
    交æµģ
    0.09
     Kimberly
    0.09
     Breitbart
    0.09
    举æŃ¢
    0.09
    (AL
    0.09
    Activations Density 0.111%

    No Known Activations