© 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. 58444
    Prev
    Next
    INDEX
    Explanations

    č legal citations

    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
    ç³Ĭæ¶Ĥ
    -0.10
    çĶļä¹Ī
    -0.09
    è´Łè´£ä»»
    -0.09
    çķĻä¸ĭæĿ¥
    -0.09
    åıijå±ķ壮大
    -0.08
    å·®å¼ĤåĮĸ
    -0.08
    åĸĺ
    -0.08
    ç¼Ļ
    -0.08
    elpers
    -0.08
    oven
    -0.08
    POSITIVE LOGITS
    å´ĩ
    0.10
    zilla
    0.09
     Harley
    0.09
    qed
    0.08
    çĶŁçī©
    0.08
     Brewer
    0.08
    çĶ°éĩİ
    0.08
    dom
    0.08
    æľ
    0.08
    ä¸įä¿¡
    0.08
    Activations Density 0.066%

    No Known Activations