© 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. 33430
    Prev
    Next
    INDEX
    Explanations

    in the context of

    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
    社ä¼ļ稳å®ļ
    -0.10
    äºĭå®ŀ
    -0.09
    éĹ·
    -0.09
    æĪij说
    -0.09
    å¹ķ
    -0.09
    å¸IJ
    -0.09
    ä¸ĸçķĮä¸Ģæµģ
    -0.08
    æĵį
    -0.08
    aktu
    -0.08
    æ³ī
    -0.08
    POSITIVE LOGITS
    ç»Ī
    0.10
    å¤§åľ°
    0.09
     Willis
    0.08
    oria
    0.08
    _IF
    0.08
    çµĤ
    0.08
    awl
    0.08
    кÑĢо
    0.08
    ifa
    0.08
     Fasc
    0.08
    Activations Density 0.113%

    No Known Activations