© 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. 40056
    Prev
    Next
    INDEX
    Explanations

    single followed by a noun

    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
     اÙĦعاÙĦÙĬ
    -0.09
    sher
    -0.09
    ound
    -0.09
    soever
    -0.09
    sembl
    -0.08
    wards
    -0.08
    finding
    -0.08
    sexual
    -0.08
    ä¾ij
    -0.08
     جاÙĨب
    -0.08
    POSITIVE LOGITS
    tons
    0.24
    verständlich
    0.14
    ctic
    0.13
    -minded
    0.12
    -ended
    0.11
     лиÑĪÑĮ
    0.11
     baÅŁÄ±na
    0.11
    ities
    0.11
    -handed
    0.11
    ChildScrollView
    0.11
    Activations Density 0.056%

    No Known Activations