© 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. 10559
    Prev
    Next
    INDEX
    Explanations

    twist and turn

    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
    éĿ¢çĽ®
    -0.09
    áŀĹ
    -0.09
    ritch
    -0.09
     Witnesses
    -0.09
    utoff
    -0.09
    rance
    -0.08
    íĦ°
    -0.08
    istration
    -0.08
    ç²ĺ
    -0.08
    ycin
    -0.08
    POSITIVE LOGITS
    转æĬĺ
    0.12
    æĽ²æĬĺ
    0.11
    è¿Ń
    0.11
    çĶŁåij½åĬĽ
    0.10
     twists
    0.10
    uess
    0.09
    é£İäºij
    0.09
    çŃĭ
    0.09
    å±ĢåĬ¿
    0.09
    车éģĵ
    0.09
    Activations Density 0.013%

    No Known Activations