© 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. 57617
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    åĿļå®ļä¸į移
    -0.09
    ocator
    -0.09
    ouden
    -0.09
    æľĢéĢĤåIJĪ
    -0.09
    çģĮ
    -0.09
     деÑıÑĤелÑĮ
    -0.08
    å¨ģ
    -0.08
    æĴ
    -0.08
     заÑı
    -0.08
    bugs
    -0.08
    POSITIVE LOGITS
    以åħį
    0.13
    çĶŁæĢķ
    0.12
    ä¸įèĩ³äºİ
    0.11
    éģ¿åħį
    0.11
    æĢķ
    0.10
    为äºĨéģ¿åħį
    0.10
    æīĵåĩ»
    0.09
     dare
    0.09
    å½ĵåľº
    0.09
     lest
    0.09
    Activations Density 0.055%

    No Known Activations