© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6566
    Prev
    Next
    INDEX
    Explanations

    smell or sound of something

    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
    _lowercase
    -0.10
    дÑĥÑĪ
    -0.09
    æĵ¿
    -0.09
    NavigationView
    -0.09
    æĦŁå®ĺ
    -0.09
    妪
    -0.09
     BCHP
    -0.09
    odash
    -0.09
    饧
    -0.09
    èľİ
    -0.09
    POSITIVE LOGITS
    /he
    0.09
    è¿ĩåIJİ
    0.09
    ube
    0.08
    æ¶Ľ
    0.08
    éĶ¡
    0.08
    ides
    0.08
    ä¿©
    0.08
    ayas
    0.08
    uggle
    0.08
    å¤±æľĽ
    0.08
    Activations Density 0.025%

    No Known Activations