© 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. 20657
    Prev
    Next
    INDEX
    Explanations

    slide presentations

    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
    åł±å°İ
    -0.09
    знаком
    -0.09
    Ñıз
    -0.09
    éĢł
    -0.09
    .iso
    -0.09
    çĽİ
    -0.09
    çĽĺ
    -0.09
    æĬ¥éģĵ
    -0.09
    ä½İä½į
    -0.09
    Stamp
    -0.08
    POSITIVE LOGITS
     slides
    0.15
     slide
    0.14
    Slides
    0.13
    slides
    0.13
     пÑĢез
    0.12
    .slide
    0.12
     Slide
    0.12
    _slide
    0.12
    Slide
    0.11
     PowerPoint
    0.11
    Activations Density 0.073%

    No Known Activations