© 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. 12147
    Prev
    Next
    INDEX
    Explanations

    performing actions

    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
    леÑĩ
    -0.10
    éħĭ
    -0.10
    ì§ĢëıĦ
    -0.09
    .oracle
    -0.09
    é£İæ³¢
    -0.09
     наÑĢ
    -0.09
    åı£åı·
    -0.09
    ched
    -0.08
    æŃ»è§Ĵ
    -0.08
    еÑģÑĮ
    -0.08
    POSITIVE LOGITS
    åįĩ
    0.09
    ç¥Ń
    0.09
     Tune
    0.08
     nue
    0.08
     acts
    0.08
    åĶ¯æľī
    0.08
     обÑıзан
    0.08
    uster
    0.08
    ancell
    0.08
    ä¿Ĺ称
    0.08
    Activations Density 0.072%

    No Known Activations