© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36078
    Prev
    Next
    INDEX
    Explanations

    Madison

    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
    ancel
    -0.10
     AFP
    -0.09
    sel
    -0.09
    微信åı·
    -0.09
    ission
    -0.08
     Apex
    -0.08
     khÄĥn
    -0.08
    àºĩ
    -0.08
    cht
    -0.08
    ç¼ĩ
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.09
    onis
    0.09
    à¹ĥà¸Ī
    0.09
    iates
    0.09
    vero
    0.09
    ashi
    0.09
    -sized
    0.09
    -sama
    0.09
    ewn
    0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    Activations Density 0.006%

    No Known Activations