© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19498
    Prev
    Next
    INDEX
    Explanations

    byte array, bytes, or byte values

    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
    rud
    -0.11
    rag
    -0.11
    £
    -0.09
    å¾Ĵ
    -0.09
    isan
    -0.09
    ner
    -0.09
    åѦ龸
    -0.09
    pet
    -0.09
    acles
    -0.09
    teenth
    -0.09
    POSITIVE LOGITS
    æĪĺ
    0.12
    ives
    0.11
    è¿Ļä¹Łæĺ¯
    0.10
    antry
    0.09
    codes
    0.09
    lotte
    0.09
    worm
    0.09
    ä¸ĢåĽŀäºĭ
    0.08
    çĺ¤
    0.08
    ingham
    0.08
    Activations Density 0.091%

    No Known Activations