© 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. 29408
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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
    istan
    -0.11
    æľŁåĨħ
    -0.09
    stown
    -0.09
    åĮºæĶ¿åºľ
    -0.09
    ectomy
    -0.09
    رت
    -0.09
    麽
    -0.09
    alin
    -0.08
    semble
    -0.08
    sters
    -0.08
    POSITIVE LOGITS
    0.14
    scape
    0.13
    éļį
    0.10
    wide
    0.10
    mun
    0.09
    OfBirth
    0.09
    apsed
    0.09
    请大家
    0.09
    bike
    0.09
    ì¦Į
    0.09
    Activations Density 0.078%

    No Known Activations