© 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. 56544
    Prev
    Next
    INDEX
    Explanations

    about beer or movie

    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
    éĤij
    -0.10
    çļĦæĶ¿æ²»
    -0.10
    çļĦæĸĩåĮĸ
    -0.10
    _PLATFORM
    -0.09
    窦
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    unes
    -0.08
    åı¼
    -0.08
    éģĴ
    -0.08
    çļĦ身ä½ĵ
    -0.08
    POSITIVE LOGITS
    è¿Ļ两ç§į
    0.10
    è¿Ļ个è¡Įä¸ļ
    0.10
    è¿Ļ个èģĮä¸ļ
    0.10
    æijĦå½±
    0.10
     disguise
    0.09
    该项
    0.09
    书æ³ķ
    0.09
    åįĩéĻį
    0.08
     photography
    0.08
    éŁ³ä¹IJ
    0.08
    Activations Density 0.636%

    No Known Activations