© 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. 30175
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    alin
    -0.10
    åıijè´¢
    -0.09
    _REGS
    -0.09
    opers
    -0.09
    ä¼
    -0.08
    èµ°åĩºæĿ¥
    -0.08
    æ¹ĸå·ŀ
    -0.08
    ument
    -0.08
    ILD
    -0.08
    ammen
    -0.08
    POSITIVE LOGITS
    并ä¸įæĦıåij³
    0.09
    æ¬²æľĽ
    0.09
    eness
    0.09
     ÙĪاست
    0.09
     erfol
    0.09
    åİŁæľī
    0.09
    象å¾ģ
    0.09
     завиÑģиÑĤ
    0.09
     ÙĪعدÙħ
    0.09
     пÑĢоиÑģÑħодиÑĤ
    0.08
    Activations Density 0.887%

    No Known Activations