© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    car body panels

    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
    åŀ¦
    -0.09
    ä¸īæľŁ
    -0.08
    uter
    -0.08
    è¿ĺ没
    -0.08
    asan
    -0.08
     consistently
    -0.08
    ç»ĵå®ŀ
    -0.08
    ç¢ij
    -0.08
    è¢ľ
    -0.08
    åĨįçİ°
    -0.08
    POSITIVE LOGITS
    éĴ¢ç»ĵæŀĦ
    0.11
    ington
    0.10
    ollision
    0.10
    åĩ¹
    0.10
    èĤ
    0.10
    éĴ£
    0.10
     اÙĦخار
    0.10
    INGTON
    0.09
    æ¡Ĩæŀ¶
    0.09
    OVE
    0.09
    Activations Density 0.126%

    No Known Activations