© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 956
    Prev
    Next
    INDEX
    Explanations

    Copyright statements

    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
    轩
    -0.10
    ÑģÑĤвоваÑĤÑĮ
    -0.10
    为ä¸Ģä½ĵ
    -0.10
    çŁ³æ²¹
    -0.09
    ellt
    -0.09
    igo
    -0.09
    è½Ń
    -0.09
    anner
    -0.09
    人æ°ijéĵ¶è¡Į
    -0.09
    гÑĥ
    -0.09
    POSITIVE LOGITS
    ìį¨
    0.10
    éĶ¹
    0.09
    漪
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    å¹ķ
    0.08
    mates
    0.08
    åħ¶æ¬¡
    0.08
    town
    0.08
    za
    0.08
    åı¯è§Ĥ
    0.08
    Activations Density 0.003%

    No Known Activations