© 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. 20528
    Prev
    Next
    INDEX
    Explanations

    any particular item

    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
    رس
    -0.09
    çĥŃæIJľ
    -0.09
    elman
    -0.09
    åİ¥
    -0.08
    è··
    -0.08
    妪
    -0.08
    åij±
    -0.08
    ationToken
    -0.08
    utex
    -0.08
    游ä¹IJ
    -0.08
    POSITIVE LOGITS
    ä¸į解
    0.09
    代
    0.09
    ä¿ĥæĪIJ
    0.09
    earer
    0.09
    åIJĦæł·
    0.09
    kers
    0.08
    ä¸ĢåĪĩ
    0.08
    橼
    0.08
    plier
    0.08
    itative
    0.08
    Activations Density 0.062%

    No Known Activations