© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51570
    Prev
    Next
    INDEX
    Explanations

    talking about discussions

    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
    è·³è·ĥ
    -0.09
    涧
    -0.09
    idar
    -0.09
    DAQ
    -0.09
    ISTR
    -0.09
    ¢åįķ
    -0.09
    aggio
    -0.09
    acci
    -0.08
     Sag
    -0.08
    Tumblr
    -0.08
    POSITIVE LOGITS
    è°Īè¯Ŀ
    0.17
    约è°Ī
    0.15
    交è°Ī
    0.12
     talked
    0.12
     conversations
    0.12
    èģĬ
    0.11
     talk
    0.11
     conversation
    0.11
    è°Īè°Ī
    0.11
    è°Ī
    0.11
    Activations Density 0.052%

    No Known Activations