© 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. 30275
    Prev
    Next
    INDEX
    Explanations

    cosplay convention

    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
    æĴŃæĬ¥
    -0.10
    ä¹IJéĺŁ
    -0.09
    çIJĥåľº
    -0.09
    èķī
    -0.08
     pf
    -0.08
    å¥ļ
    -0.08
    éĽĩ
    -0.08
    ä¹į
    -0.08
     Ui
    -0.08
     benchmark
    -0.08
    POSITIVE LOGITS
     cosplay
    0.11
    ÑĨев
    0.09
    éĿ¢å®¹
    0.09
    浸
    0.08
    ноÑģÑĤ
    0.08
     unas
    0.08
    å¤ĸå½¢
    0.08
    åĬ¨æ¼«
    0.08
    ItemType
    0.08
    åıijè¡Į
    0.08
    Activations Density 0.158%

    No Known Activations