© 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. 36082
    Prev
    Next
    INDEX
    Explanations

    Gulf of geographic locations

    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
    ivil
    -0.09
    hare
    -0.09
    upert
    -0.09
    ements
    -0.08
    entials
    -0.08
    lius
    -0.08
    é¹ħ
    -0.08
    ç´IJ
    -0.08
    archy
    -0.08
    etable
    -0.08
    POSITIVE LOGITS
    è®¤çľŁåŃ¦ä¹ł
    0.11
    side
    0.11
    æ¯ı个人éĥ½
    0.10
    ierrez
    0.10
    æ£ĺ
    0.09
    errat
    0.09
     ÐľÐ¾ÑģквÑĭ
    0.09
    inator
    0.09
    izar
    0.09
    DidChange
    0.09
    Activations Density 0.007%

    No Known Activations