© 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. 53260
    Prev
    Next
    INDEX
    Explanations

    time between intervals

    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
    åĪĨ解
    -0.10
    æĻĶ
    -0.09
     Ø¢ÙĦ
    -0.09
    çĺ¾
    -0.09
    é¦Ĩ
    -0.09
    ä¾£
    -0.09
    åĽ´è§Ĥ
    -0.09
    orris
    -0.09
    éĺİ
    -0.08
    gne
    -0.08
    POSITIVE LOGITS
    éĹ´éļĶ
    0.16
    ä¹ĭéĹ´
    0.15
    ä¹ĭéĹ´çļĦ
    0.14
    _between
    0.13
    ä¹ĭéĸĵ
    0.13
    between
    0.12
     between
    0.12
     BETWEEN
    0.12
    éĹ´éļĻ
    0.12
     междÑĥ
    0.12
    Activations Density 0.076%

    No Known Activations