© 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. 57698
    Prev
    Next
    INDEX
    Explanations

    personal statements and future intentions

    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
    å¼ķ
    -0.10
    ä¸įåºĶ该
    -0.09
    å®ľ
    -0.09
    è¶ģçĿĢ
    -0.09
     Pers
    -0.08
    æĢİä¹Ī说
    -0.08
    utos
    -0.08
    è¶ģ
    -0.08
    åŃĹæ¯į
    -0.08
    æķĪ
    -0.08
    POSITIVE LOGITS
    åĽŀåºĶ
    0.10
    æģ¼
    0.10
    åĽŀé¦Ī
    0.09
    Respond
    0.09
    æī¿è¯º
    0.09
     неÑģк
    0.09
    æİ¥åıĹäºĨ
    0.09
    ÑĢÑĥд
    0.09
    åĸīåĴĻ
    0.09
     respond
    0.09
    Activations Density 0.046%

    No Known Activations