© 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. 24120
    Prev
    Next
    INDEX
    Explanations

    trust and deserving

    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
    Negative Logits
    zac
    -0.09
    çĶº
    -0.08
    马æĭīæĿ¾
    -0.08
    è·¨
    -0.08
    erk
    -0.08
    rex
    -0.08
     Biz
    -0.08
    åı®
    -0.08
    деÑĢ
    -0.08
     Creed
    -0.07
    POSITIVE LOGITS
    worthy
    0.14
    ably
    0.13
    ingly
    0.12
    worth
    0.12
    upert
    0.11
    fully
    0.10
    ful
    0.10
    ÙĪÙĨÙĬ
    0.10
    èѦæĸ¹
    0.10
    å·²ä¹ħçļĦ
    0.10
    Activations Density 0.007%

    No Known Activations