© 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. 16906
    Prev
    Next
    INDEX
    Explanations

    where... becomes interesting

    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
     Alv
    -0.09
    à¹Ĥà¸Ķย
    -0.09
    تÙĨا
    -0.09
    ucher
    -0.09
     ThÆ°
    -0.08
    viously
    -0.08
    ussed
    -0.08
     Comey
    -0.08
    IVES
    -0.08
    å¾Ĺèµ·
    -0.08
    POSITIVE LOGITS
    åĢŁ
    0.10
    è·Ħ
    0.10
    ä¸Ģç¬Ķ
    0.09
    (exports
    0.09
    两ä½į
    0.08
    çĭ¸
    0.08
    å°±å¼Ģå§ĭ
    0.08
    åĢŁçĶ¨
    0.08
    ocha
    0.08
    çĥŁ
    0.08
    Activations Density 0.027%

    No Known Activations