© 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. 21042
    Prev
    Next
    INDEX
    Explanations

    comma-separated strings and lists

    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
    cling
    -0.10
    unch
    -0.09
    寮
    -0.09
    åĮł
    -0.09
    å¹³åİŁ
    -0.09
    schlie
    -0.09
     пÑĢиÑĩин
    -0.09
    ä½ŀ
    -0.09
    åľ¨å¤ĸ
    -0.09
    ä¹ľ
    -0.09
    POSITIVE LOGITS
     comma
    0.11
     commas
    0.11
     separated
    0.10
     separation
    0.10
    éĢĹ
    0.09
    comma
    0.09
    éļĶ
    0.09
    Separated
    0.09
     SEP
    0.09
    -separated
    0.08
    Activations Density 0.094%

    No Known Activations