© 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. 63761
    Prev
    Next
    INDEX
    Explanations

    too much or many

    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
    ãģĨãģ¡ãģ«
    -0.10
     toch
    -0.09
    uit
    -0.08
     thus
    -0.08
    melon
    -0.08
    ninger
    -0.08
    足
    -0.08
    æįį
    -0.08
     maint
    -0.08
    thus
    -0.08
    POSITIVE LOGITS
    ooting
    0.10
    avn
    0.09
    ledo
    0.09
    ãĥŃãĥ¼
    0.09
    erot
    0.09
    ÑĪен
    0.09
    çĤĸ
    0.09
    alance
    0.08
    ãģĹãĤĩãģĨ
    0.08
    lections
    0.08
    Activations Density 0.024%

    No Known Activations