© 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. 58852
    Prev
    Next
    INDEX
    Explanations

    cell imaging and diagnosis

    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
    ç¾İ好çĶŁæ´»
    -0.09
    è¿Ľåľº
    -0.09
    è¿Ļä¹Īå¤ļå¹´
    -0.09
    è¿Ļä¹Ī大
    -0.08
    OLE
    -0.08
    _sz
    -0.08
    $$$$
    -0.08
    ole
    -0.08
    (sr
    -0.08
    ä¸ŃåĽ½çī¹èī²
    -0.08
    POSITIVE LOGITS
    çİ»
    0.10
    곤
    0.10
    æĹ¶å¸¸
    0.10
    å¹²æ¶ī
    0.10
    èĦ©
    0.09
     Zen
    0.09
    çİ»çĴĥ
    0.09
    å½ķåĥı
    0.09
    æİĩ
    0.09
     glass
    0.09
    Activations Density 0.272%

    No Known Activations