© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9588
    Prev
    Next
    INDEX
    Explanations

    similar or suitable

    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
    çĶ³
    -0.09
    issing
    -0.09
     frank
    -0.09
    rames
    -0.08
     Cler
    -0.08
    éĿ¢åŃIJ
    -0.08
     spelling
    -0.08
    brace
    -0.08
    ä¾ĭå¤ĸ
    -0.08
    bios
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.13
    æ¯Ķå¦Ĥ
    0.12
    èѬå¦Ĥ
    0.12
    类似çļĦ
    0.11
    éĢĤå½ĵ
    0.10
    åIJĪéĢĤçļĦ
    0.10
    éĢĤå½ĵçļĦ
    0.10
    级以ä¸Ĭ
    0.10
    主æµģ
    0.10
    åĪ«çļĦ
    0.10
    Activations Density 0.219%

    No Known Activations