© 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. 16908
    Prev
    Next
    INDEX
    Explanations

    entire X

    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
     intim
    -0.11
    goo
    -0.10
    ERA
    -0.09
    pile
    -0.09
    обÑĢаз
    -0.09
    ×ķת
    -0.09
    ðŁı¼
    -0.09
    UM
    -0.09
    ron
    -0.08
    riet
    -0.08
    POSITIVE LOGITS
    ties
    0.13
    phin
    0.12
    MENT
    0.11
    ment
    0.11
    ials
    0.11
    maal
    0.11
    íŀĪ
    0.11
    ities
    0.10
    CriticalSection
    0.10
     лиÑĪÑĮ
    0.10
    Activations Density 0.014%

    No Known Activations