© 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. 39960
    Prev
    Next
    INDEX
    Explanations

    groundbreaking research and work

    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
    until
    -0.09
    _until
    -0.09
    à¦
    -0.08
    伪
    -0.08
    atives
    -0.08
    ãģĭãĤĬ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    ification
    -0.08
     Sunshine
    -0.08
    ä¸Ĭåįĥ
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.12
    æĢ§çļĦ
    0.11
    èĢħçļĦ
    0.10
    ãĥķãĤ©ãĥ¼
    0.10
    年第
    0.10
    æ¶ķ
    0.09
    ÑİÑī
    0.09
     ÅŁeyler
    0.09
    åĴ
    0.09
    è§ij
    0.09
    Activations Density 0.013%

    No Known Activations