© 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. 23845
    Prev
    Next
    INDEX
    Explanations

    by means of

    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
     Liber
    -0.09
    åħį
    -0.09
    jak
    -0.09
    å¸IJåı·
    -0.09
    undle
    -0.09
    аÑĢи
    -0.08
    é¢Ĩ导
    -0.08
    足迹
    -0.08
    ÑĪив
    -0.08
    udeau
    -0.08
    POSITIVE LOGITS
    åĤį
    0.11
    éĿł
    0.10
    åIJ¬åıĸ
    0.10
    å¹²äºĭ
    0.09
    urus
    0.09
    æīĵå¼Ģ
    0.09
    åIJ¬
    0.09
     ÑĩÑĤ
    0.08
     deposit
    0.08
    irt
    0.08
    Activations Density 0.168%

    No Known Activations