© 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. 23895
    Prev
    Next
    INDEX
    Explanations

    breed specification

    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
     saf
    -0.09
    åľ°çĤ¹
    -0.09
    avn
    -0.09
    Veter
    -0.09
    pdev
    -0.09
    CRM
    -0.09
    drm
    -0.08
    à¬Ĩ
    -0.08
    åĸľ
    -0.08
    -Identifier
    -0.08
    POSITIVE LOGITS
    强壮
    0.12
    æŃ£å®Ĺ
    0.11
    å°½æĹ©
    0.10
    ç¥ĸåħĪ
    0.10
    æķ£çĥŃ
    0.10
    çļĦæ¯ĶèµĽ
    0.10
    æ¨¡æł·
    0.09
     жиз
    0.09
    illian
    0.09
    çļĦæĢ§æł¼
    0.09
    Activations Density 0.055%

    No Known Activations