© 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. 40333
    Prev
    Next
    INDEX
    Explanations

    advertising agency

    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
     subj
    -0.10
    åĴ½
    -0.09
    ATEGORIES
    -0.08
    ãĤ¹ãĥŀãĥĽ
    -0.08
    ä¿®çIJĨ
    -0.08
    ç½ijè´Ń
    -0.08
    imestep
    -0.08
    builder
    -0.08
    åĵ²
    -0.08
    _NOTIFY
    -0.08
    POSITIVE LOGITS
    广åijĬ
    0.10
    廣åijĬ
    0.10
     Advertising
    0.10
     campaign
    0.10
    PRETTY
    0.09
    å¸ĥ
    0.09
    åªĴä»ĭ
    0.09
    Advertising
    0.09
    Campaign
    0.09
    广åijĬæľįåĬ¡
    0.09
    Activations Density 0.129%

    No Known Activations