© 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. 27450
    Prev
    Next
    INDEX
    Explanations

    overstock, clearance, liquidation, grade items

    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
    INY
    -0.10
    太å°ij
    -0.09
    羸
    -0.08
     пÑĢедÑĥÑģмоÑĤÑĢ
    -0.08
    æĿŁ
    -0.08
    éĻĨç»Ń
    -0.08
    æľĶ
    -0.08
     IGN
    -0.08
    ç»ıèIJ¥
    -0.08
     Mid
    -0.08
    POSITIVE LOGITS
     Derm
    0.09
    å½
    0.09
    ired
    0.08
    umi
    0.08
     dermat
    0.08
    ç¨į
    0.08
    dings
    0.08
    _CHAN
    0.08
    .bb
    0.08
    è¿ijä¹İ
    0.08
    Activations Density 0.036%

    No Known Activations