© 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. 10239
    Prev
    Next
    INDEX
    Explanations

    time elapsed since an event

    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
     اÙĦبÙĦ
    -0.10
    èĥ½è¾¾åĪ°
    -0.09
    .rdf
    -0.09
    ä¸įåIJĥ
    -0.08
    æĤĦ
    -0.08
    ä¹Łæĺ¯ä¸Ģç§į
    -0.08
    à¸Ĥà¸Ńà¸ļ
    -0.08
     increasingly
    -0.08
     Tear
    -0.08
    ä»°
    -0.08
    POSITIVE LOGITS
    æĺ¨æĹ¥
    0.11
    ä¸įä¹ħ
    0.10
    æĮ¥
    0.10
    é²ľæ´»
    0.10
    说æľį
    0.09
    ARED
    0.09
    åľ°å¸¦
    0.09
    cen
    0.09
     Cabinet
    0.09
    ish
    0.09
    Activations Density 0.026%

    No Known Activations