© 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. 30425
    Prev
    Next
    INDEX
    Explanations

    license, suite, public, data, entity

    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
     Dias
    -0.09
    ä¸įåIJĪ
    -0.09
    shi
    -0.09
     ÙĪغÙĬر
    -0.09
    Incoming
    -0.08
     turno
    -0.08
    ç«ĭ
    -0.08
    ENS
    -0.08
    åį¸
    -0.08
    管åĪ¶
    -0.08
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.09
    è°ĥåīĤ
    0.09
    è¿ĺåľ¨
    0.08
    quot
    0.08
    pics
    0.08
    ÙĪس
    0.08
    çĶ»éĿ¢
    0.08
    æľīä¸Ģå®ļ
    0.08
    é£İ湿
    0.08
    滨
    0.08
    Activations Density 0.004%

    No Known Activations