© 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. 47664
    Prev
    Next
    INDEX
    Explanations

    but still / for / where / then / immediately / he / only

    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
    åĽºçĦ¶
    -0.13
    دÙĬØ©
    -0.10
    æŀľçĦ¶
    -0.10
     zwar
    -0.10
    å½ĵçĦ¶
    -0.09
    çļĦç¡®
    -0.09
    éĥ½è¯´
    -0.09
    è¦ģä¹Ī
    -0.09
    поÑĩÑĤ
    -0.09
    .if
    -0.08
    POSITIVE LOGITS
    ä»įæľī
    0.10
    ä¸įéĢļ
    0.09
    ä¸įä¹ħ
    0.09
    æĹ©åľ¨
    0.09
    çķĻä¸ĭäºĨ
    0.08
    è¿ĺæľī
    0.08
    ä»įåľ¨
    0.08
    è¿ĺæľª
    0.08
     около
    0.08
    éĤĦæľī
    0.08
    Activations Density 0.100%

    No Known Activations