© 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. 30454
    Prev
    Next
    INDEX
    Explanations

    maximum accuracy

    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
    积累äºĨ
    -0.09
     Pierce
    -0.09
    magnitude
    -0.08
     magnitude
    -0.08
    è¶ģ
    -0.08
    Magnitude
    -0.08
     Gates
    -0.08
    anta
    -0.08
    æľĢæľī
    -0.08
    ä¿Ĥ
    -0.07
    POSITIVE LOGITS
    æĢ§èĥ½
    0.12
    ç³ľ
    0.12
    æ²¹èĢĹ
    0.12
     performance
    0.11
    ç¨Ĺ
    0.10
    åĬŁ
    0.10
    ä½ļ
    0.10
    ç»ŃèĪª
    0.10
     заÑıв
    0.09
     Performance
    0.09
    Activations Density 0.027%

    No Known Activations