© 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. 22894
    Prev
    Next
    INDEX
    Explanations

    most + adjective/adverb

    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
    æŀģèĩ´
    -0.10
     Limits
    -0.09
    家ä½ı
    -0.09
    çĶ³
    -0.09
    æŀģåĵģ
    -0.09
     Ñģебе
    -0.09
    èĮ±
    -0.09
    æ²»
    -0.08
    ç»Īæŀģ
    -0.08
    fore
    -0.08
    POSITIVE LOGITS
    most
    0.11
     most
    0.10
    clo
    0.09
    çªģåĩºéĹ®é¢ĺ
    0.09
     наиболее
    0.09
    azzi
    0.09
    ocol
    0.09
    æľĢãĤĤ
    0.09
    ocom
    0.09
    社ä¼ļåıijå±ķ
    0.09
    Activations Density 0.054%

    No Known Activations