© 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. 8804
    Prev
    Next
    INDEX
    Explanations

    batch processing or API

    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
    ÑģÑĤой
    -0.09
    éģIJ
    -0.09
    éĤ¦
    -0.08
    ances
    -0.08
    Į
    -0.08
    liest
    -0.08
    ble
    -0.07
    ä¸įäºĨ
    -0.07
    apolis
    -0.07
    EMA
    -0.07
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.13
    elor
    0.12
    mates
    0.12
    aroo
    0.12
    edImage
    0.11
    elder
    0.11
    norm
    0.10
    urre
    0.10
    rooms
    0.10
    æĪijä»¬çŁ¥éģĵ
    0.10
    Activations Density 0.014%

    No Known Activations