© 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. 17103
    Prev
    Next
    INDEX
    Explanations

    scientific publication sections

    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
    зоÑĢ
    -0.12
    æľºçĶµ
    -0.10
    unken
    -0.10
    åĪijäºĭæ¡Ī件
    -0.10
    éĻ·éĺ±
    -0.09
    ODE
    -0.09
     Ñĩем
    -0.09
    -multi
    -0.09
    ieten
    -0.09
    Dies
    -0.09
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.09
    êµIJ
    0.08
    ä¸į该
    0.08
    воз
    0.08
    (sc
    0.08
    ä¼ī
    0.07
    å°±åĮ»
    0.07
    PEG
    0.07
    æİĩ
    0.07
     mere
    0.07
    Activations Density 0.200%

    No Known Activations