© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    after-tax profit

    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
    çĭ·
    -0.09
    å½ĵåĪĿ
    -0.08
    æĺ¨æĹ¥
    -0.08
    éĶĢåĶ®æ¸łéģĵ
    -0.08
    æĮij
    -0.08
     sell
    -0.08
    ç³ł
    -0.08
    çĤŃ
    -0.08
     comercial
    -0.08
    çĸı
    -0.08
    POSITIVE LOGITS
    /save
    0.10
    ebile
    0.10
    .Modules
    0.10
    NEY
    0.10
    çļĦä¸Ģ项
    0.10
    æħİ
    0.09
    isms
    0.09
    èĬĤçľģ
    0.09
     доÑģÑĤ
    0.09
    azzi
    0.09
    Activations Density 0.042%

    No Known Activations