© 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. 9178
    Prev
    Next
    INDEX
    Explanations

    instrumentation

    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
    sWith
    -0.14
    able
    -0.12
    swith
    -0.11
    ãģ¾ãģ¾
    -0.10
    omat
    -0.10
    (s
    -0.09
    sh
    -0.09
    们çļĦ
    -0.09
    箸
    -0.09
    éĥ
    -0.09
    POSITIVE LOGITS
    ¨
    0.10
    ayer
    0.09
    æѤåĪ»
    0.09
    ross
    0.09
    uxe
    0.09
    наÑĤ
    0.08
    ount
    0.08
     Dor
    0.08
    ifr
    0.08
    ound
    0.08
    Activations Density 0.362%

    No Known Activations