© 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. 55887
    Prev
    Next
    INDEX
    Explanations

    point in

    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
    åŁı
    -0.09
    çĵ·
    -0.09
    tur
    -0.09
    åŀ£
    -0.09
    allee
    -0.08
     Ston
    -0.08
    itung
    -0.08
    åı¯æĢķçļĦ
    -0.08
    åķĨåĬ¡
    -0.08
    èIJį
    -0.08
    POSITIVE LOGITS
    æī¹ç¤º
    0.09
    ä¾Ħ
    0.09
    æľºä½ĵ
    0.09
    çľ·
    0.09
     деÑĢ
    0.09
    antee
    0.08
    rial
    0.08
     ApiException
    0.08
    åĽŀäºĭ
    0.08
     neph
    0.08
    Activations Density 0.125%

    No Known Activations