© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    manner or degree adverbs

    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
    ed
    -0.08
    liable
    -0.08
    овÑĭй
    -0.08
    è¹ĭ
    -0.08
    imed
    -0.08
    è®°è½½
    -0.08
    èĭķ
    -0.07
    èĥ¥
    -0.07
    razione
    -0.07
    patrick
    -0.07
    POSITIVE LOGITS
    人们çļĦ
    0.10
    åħ³äºİæĪij们
    0.10
    è¿Ļæł·çļĦè¯Ŀ
    0.10
    ä½ľä¸ºä¸ĢåIJį
    0.10
    以åħį
    0.10
    è¿ĻéĩĮæľī
    0.09
     ÙĦÙĦغا
    0.09
    éĢīåĩº
    0.09
    éĹº
    0.09
     enough
    0.09
    Activations Density 0.240%

    No Known Activations