© 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. 17108
    Prev
    Next
    INDEX
    Explanations

    Hawaii and Miami

    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
    å·¥æľŁ
    -0.10
    ural
    -0.09
    urre
    -0.09
    è¿´
    -0.09
    ÙĪØ·
    -0.09
    累累
    -0.08
    otation
    -0.08
    uxe
    -0.08
    à¹Ĥà¸Ħร
    -0.08
    åĬŀ好
    -0.08
    POSITIVE LOGITS
    ç¤ģ
    0.10
    ensis
    0.10
    ç¾¤å²Ľ
    0.10
     Islands
    0.10
    å°±æĺ¯åľ¨
    0.10
    å·ŀ
    0.09
    iya
    0.09
    èĩªæ²»åĮº
    0.09
    ëĵĿ
    0.09
    пиÑĤ
    0.09
    Activations Density 0.005%

    No Known Activations