© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    organization names

    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
    寸
    -0.11
    è®Ń
    -0.09
    еÑĩа
    -0.09
    ç¡ķ
    -0.09
    æ¾İæ¹ĥ
    -0.08
    ä½ĵåĪ¶
    -0.08
    çĥŃè¡Ģ
    -0.08
    èĥ¸åı£
    -0.08
    éĽªå±±
    -0.08
    驳
    -0.08
    POSITIVE LOGITS
    èµĦæĸĻæĺ¾ç¤º
    0.10
    çłĶ究表æĺİ
    0.10
    ç»ŀ
    0.09
    æ¯ıå¹´
    0.09
    æ¯ıå¹´éĥ½
    0.09
    说è¿ĩ
    0.09
    åħ³äºİ
    0.09
    认为
    0.09
    itionally
    0.09
    äºĨ许å¤ļ
    0.08
    Activations Density 0.331%

    No Known Activations