© 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. 49189
    Prev
    Next
    INDEX
    Explanations

    www

    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
    å¤ļ彩
    -0.10
    å¹Į
    -0.09
    çļĤ
    -0.08
    诳
    -0.08
    æŃī
    -0.08
     полÑĮзÑĥ
    -0.08
    iban
    -0.08
    çĽ¸äº²
    -0.08
    åłĥ
    -0.08
    åĮĹ京åĨ¬å¥¥
    -0.08
    POSITIVE LOGITS
    обилÑĮ
    0.09
    åīįåįģ
    0.09
    jay
    0.09
    à¹Ģฮ
    0.08
    efs
    0.08
     báºŃt
    0.08
    龸çİĭ
    0.08
    çIJĨçĶ±
    0.08
    è·³åĩº
    0.08
     пÑĢогноз
    0.08
    Activations Density 0.130%

    No Known Activations