© 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. 27924
    Prev
    Next
    INDEX
    Explanations

    technical and academic contexts

    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
    ä¸ĢåĪĨéĴ±
    -0.12
    ä¸įèµ·
    -0.10
    çļĦä¸ĢäºĽ
    -0.10
    memberof
    -0.10
    éĤ£äºĽ
    -0.10
    ä¸ĢèĪ¬éĥ½æĺ¯
    -0.09
    ãģŁãģı
    -0.09
    çķĽ
    -0.09
    æ®ģ
    -0.09
    ackers
    -0.09
    POSITIVE LOGITS
    æĤī
    0.09
     opts
    0.08
    ç»ĦæĪIJçļĦ
    0.08
     Fil
    0.08
    çĶµåŃIJéĤ®ä»¶
    0.08
    å®ŀå¹²
    0.07
     Gre
    0.07
    è¿Ŀ
    0.07
    opt
    0.07
    è¢ĸ
    0.07
    Activations Density 0.390%

    No Known Activations