© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20313
    Prev
    Next
    INDEX
    Explanations

    much needed, more, pride, earlier

    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
    æŁIJç§į
    -0.10
    ends
    -0.10
    ä¸ĩä¸Ģ
    -0.09
    ÑģÑĤо
    -0.09
     somehow
    -0.09
    æľīä¸Ģ天
    -0.09
    çªĿ
    -0.08
    yll
    -0.08
    (END
    -0.08
     maybe
    -0.08
    POSITIVE LOGITS
    -needed
    0.12
    å¤ĸåĽ´
    0.10
    æ¶īæ¡Ī
    0.09
    æĹ©åľ¨
    0.09
    orable
    0.09
    æIJĢ
    0.08
    urple
    0.08
    æѤäºĭ
    0.08
    äºĨå¾Īä¹ħ
    0.08
    èIJ¦
    0.08
    Activations Density 0.014%

    No Known Activations