© 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. 50556
    Prev
    Next
    INDEX
    Explanations

    geosphere, surface, mantle, ocean

    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®ŀçī©
    -0.10
    æĬ¢æķij
    -0.09
    èºį
    -0.09
    onia
    -0.09
     Purdue
    -0.09
    è·ĥ
    -0.09
    æ¯ķ
    -0.08
    aight
    -0.08
    æ·¡
    -0.08
    èĤĿ
    -0.08
    POSITIVE LOGITS
    æµģæ°´
    0.10
    çĥŃæ°´
    0.09
    IVO
    0.09
    å°ı鸣
    0.09
    ä¹°åįĸ
    0.08
    ä¸ĭæīĭ
    0.08
    -hot
    0.08
    æµ·å²Ľ
    0.08
     meth
    0.08
    æµ·æ°´
    0.08
    Activations Density 0.078%

    No Known Activations