© 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. 57812
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    åŨ
    -0.10
    å®īçĦ¶
    -0.10
    bah
    -0.09
    uges
    -0.09
    çijĻ
    -0.09
    æĬķåħ¥åĪ°
    -0.09
    ocol
    -0.09
    太å¤ļçļĦ
    -0.09
    loy
    -0.09
    berger
    -0.09
    POSITIVE LOGITS
    ÙĨس
    0.10
    éĢ¢
    0.09
    åŃIJå¼¹
    0.09
    åľĪ
    0.08
    zem
    0.08
    SIM
    0.08
     Wig
    0.08
    er
    0.08
    Tes
    0.08
     ÐĺÑģ
    0.08
    Activations Density 0.001%

    No Known Activations