© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    not to

    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
    berger
    -0.09
    æķ¢
    -0.09
    urm
    -0.09
    æĮĩ示
    -0.08
    ddl
    -0.08
    åģ¶
    -0.08
    athe
    -0.08
    ntl
    -0.08
    表éĿ¢
    -0.08
    rou
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.14
    åĽłä¸ºæĪij们
    0.11
    lah
    0.11
    çĦ¶æĺ¯
    0.10
    æĪij们éĥ½
    0.09
    éķ¦
    0.09
    çļĦæĹ¥åŃIJéĩĮ
    0.09
    å¸ĤåĮº
    0.09
    èĢģ人家
    0.09
    ãģªãĤīãģªãģĦ
    0.09
    Activations Density 0.011%

    No Known Activations