© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    finale

    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
    URT
    -0.10
    éĿŀ常好çļĦ
    -0.09
    ering
    -0.09
    mint
    -0.09
     fart
    -0.09
    ì°Į
    -0.09
    çĥ¯
    -0.08
    озв
    -0.08
    bilt
    -0.08
    обÑĢаз
    -0.08
    POSITIVE LOGITS
    ous
    0.11
    ãĤĴè¿İ
    0.11
    çļĦåĪ°æĿ¥
    0.10
    ä¹ĭä½ľ
    0.10
    æīĢåľ¨
    0.10
    ãģ¾ãģĹãģ¦
    0.10
    è¿Ń
    0.09
    人çī©
    0.09
    äºĨä¸Ģåľº
    0.09
    对åĨ³
    0.09
    Activations Density 0.006%

    No Known Activations