© 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. 54208
    Prev
    Next
    INDEX
    Explanations

    technical language context

    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
    èIJ
    -0.09
     Chu
    -0.08
     Dakota
    -0.07
    å·²ç»ı被
    -0.07
    ä»ĭç»įäºĨ
    -0.07
    ä»ŀ
    -0.07
    åĭ¾
    -0.07
    ä»ĸæĽ¾
    -0.07
    ä½łåĸľæ¬¢
    -0.07
    ä¸ŃåĽ½äººæ°ij
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.14
    åīįèĢħ
    0.12
    å½ĵä¹ĭ
    0.12
    两èĢħ
    0.10
    æīįæĺ¯çľŁæŃ£
    0.10
    æĽ´èĥ½
    0.10
    å±ŀäºİèĩªå·±
    0.09
    纯粹
    0.09
    åIJİèĢħ
    0.09
    çŃĶåį·
    0.09
    Activations Density 0.343%

    No Known Activations