© 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. 55930
    Prev
    Next
    INDEX
    Explanations

    hydraulic circuits, rock, auger, jack, brake

    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®ĥ
    -0.09
    ãģªãģĭ
    -0.08
    èĪĢ
    -0.08
    ner
    -0.08
    ÑĢай
    -0.08
     Ä°n
    -0.08
    éĿ¢åŃIJ
    -0.08
    defgroup
    -0.08
    èī¯å¿ĥ
    -0.08
    .onCreate
    -0.08
    POSITIVE LOGITS
    ITY
    0.11
    ity
    0.10
    主宰
    0.10
    pped
    0.09
    æĶ¾å¼ĥäºĨ
    0.09
    大家éĥ½
    0.09
    itÃł
    0.08
    /photo
    0.08
    ä¸īçĤ¹
    0.08
    tte
    0.08
    Activations Density 0.030%

    No Known Activations