© 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. 36051
    Prev
    Next
    INDEX
    Explanations

    Indian Ocean, Observation System, tropical

    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
    ç¨
    -0.10
    ä¼¢
    -0.10
    OSE
    -0.09
    agg
    -0.08
     discount
    -0.08
     JMP
    -0.08
    HEL
    -0.08
     Brow
    -0.08
    pard
    -0.08
     Redistributions
    -0.08
    POSITIVE LOGITS
    è£ħå¤ĩåĪ¶éĢł
    0.11
    è£ħå¤ĩ
    0.11
    è¿ľæ´ĭ
    0.10
    æĺ¼å¤ľ
    0.09
    大æ´ĭ
    0.09
    åĬŁè¯¾
    0.09
    endar
    0.09
    å°ijåIJĥ
    0.09
    好è¿IJ
    0.09
    ç§ijåŃ¦å®¶
    0.09
    Activations Density 0.076%

    No Known Activations