© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34975
    Prev
    Next
    INDEX
    Explanations

    perpetual or continuation

    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
    éĢIJæŃ¥
    -0.09
    abwe
    -0.08
    éħ¬
    -0.08
    足迹
    -0.08
    æł·çļĦ
    -0.08
    ability
    -0.08
    çĶŁäº§æĢ»åĢ¼
    -0.08
    æļĤæŶ
    -0.08
    бÑĭ
    -0.08
    ruptcy
    -0.08
    POSITIVE LOGITS
    ively
    0.12
     Ñģобой
    0.11
    erno
    0.11
    -motion
    0.10
    emente
    0.10
    lict
    0.10
    ently
    0.10
    een
    0.09
    oftware
    0.09
    é««
    0.09
    Activations Density 0.008%

    No Known Activations