© 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. 9777
    Prev
    Next
    INDEX
    Explanations

    booking and reservation

    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
    ahir
    -0.10
    beck
    -0.10
    uzzi
    -0.10
    æķij人
    -0.10
     transc
    -0.10
    çİĭèĢħ
    -0.09
    å·¥ä½ľæĸ¹æ¡Ī
    -0.08
    alist
    -0.08
    èĤī
    -0.08
    ç£ħ
    -0.08
    POSITIVE LOGITS
    é¹Ĭ
    0.10
    Made
    0.10
    ä¸Ĭç½ij
    0.10
    訾
    0.09
     trì
    0.09
     Ñģм
    0.09
    ingen
    0.09
    æŀ§
    0.09
     اÙĦÙħÙĩ
    0.09
    ä¿ı
    0.08
    Activations Density 0.018%

    No Known Activations