© 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. 52556
    Prev
    Next
    INDEX
    Explanations

    body parts followed by 'the'

    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
    åĶ¯
    -0.10
    çļĦéĴ±
    -0.10
    åŀ£
    -0.10
     Exhaust
    -0.09
    .apple
    -0.09
    æ§
    -0.09
    mine
    -0.09
    iren
    -0.09
    ä½
    -0.09
    bai
    -0.09
    POSITIVE LOGITS
    èĦijè¢ĭ
    0.09
    ignet
    0.09
    åĿIJ
    0.08
    æīĭä¸Ĭ
    0.08
    æīĵè´¥
    0.08
    æī¾äºĨ
    0.08
    zÄħd
    0.08
    ắng
    0.08
    èħł
    0.08
    仪表
    0.08
    Activations Density 0.010%

    No Known Activations