© 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. 8027
    Prev
    Next
    INDEX
    Explanations

    main function or menu

    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
    ting
    -0.10
    anner
    -0.10
    inox
    -0.10
    ä¸ĵ项è¡ĮåĬ¨
    -0.09
    羣æŃ£åģļåĪ°
    -0.09
    mos
    -0.09
    满满
    -0.09
    ÐŀÐĿ
    -0.09
    /am
    -0.09
    rego
    -0.09
    POSITIVE LOGITS
    stay
    0.19
    enance
    0.14
    ardi
    0.12
    åİŁåĽłæĺ¯
    0.11
    imum
    0.11
    èī²è°ĥ
    0.11
    ifest
    0.11
    flux
    0.10
    udd
    0.10
    ellaneous
    0.10
    Activations Density 0.060%

    No Known Activations