© 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. 2473
    Prev
    Next
    INDEX
    Explanations

    not or may be

    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
     thus
    -0.12
     zwar
    -0.11
    çĶļèĩ³è¿ĺ
    -0.10
    èĻ½çĦ¶
    -0.10
    æĸ¼æĺ¯
    -0.10
    èĻ½çĦ¶æĺ¯
    -0.10
    äºİæĺ¯
    -0.09
    åħĪæĺ¯
    -0.09
    åıįåĢĴ
    -0.09
    thus
    -0.09
    POSITIVE LOGITS
     nevertheless
    0.11
     nonetheless
    0.11
    ä¹Łæľī
    0.09
    adol
    0.09
    ä¾ĿçĦ¶
    0.09
     ìķĬëĬĶ
    0.09
    леÑĢ
    0.09
    terior
    0.09
    ä¹Łèĥ½
    0.09
    ŧ
    0.09
    Activations Density 0.183%

    No Known Activations