© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    Il Divo, omerular injuries, Progress

    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
    çĻĸ
    -0.10
     uÄŁ
    -0.09
    æĿ³
    -0.09
    çıŃç»Ħ
    -0.09
    anca
    -0.09
    PAIR
    -0.09
    éģ¥è¿ľ
    -0.08
    .timedelta
    -0.08
    dden
    -0.08
    æŶæķĪ
    -0.08
    POSITIVE LOGITS
    /or
    0.09
    èĭ¥å¹²
    0.09
    å°ij许
    0.08
     jud
    0.08
     Dr
    0.08
    _protocol
    0.07
    еÑģÑĮ
    0.07
    åīįæīĢ
    0.07
    å¤ĸéĿ¢
    0.07
    çıħ
    0.07
    Activations Density 0.016%

    No Known Activations