© 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. 61400
    Prev
    Next
    INDEX
    Explanations

    continuously differentiable

    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
    è´¶
    -0.11
    ä¸įæľį
    -0.11
    æľīä¿¡å¿ĥ
    -0.10
    æĴ·
    -0.10
    ä¸įçķĻ
    -0.10
    åĢĶ
    -0.10
    ç¼Ń
    -0.10
    寸
    -0.10
    æĶ»åĿļæĪĺ
    -0.09
    mente
    -0.09
    POSITIVE LOGITS
    WebHost
    0.09
    PAD
    0.09
    enary
    0.08
    uster
    0.08
    distributed
    0.08
    pad
    0.08
     pad
    0.07
    åIJĮæŶè¿ĺ
    0.07
    ory
    0.07
    ker
    0.07
    Activations Density 0.136%

    No Known Activations