© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    reverse, reversed, overturned

    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
    gel
    -0.09
    suite
    -0.09
    oves
    -0.08
     Primitive
    -0.08
    pu
    -0.08
    人åĿĩ
    -0.08
    geries
    -0.08
    pole
    -0.08
    çĤ®
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    POSITIVE LOGITS
    ä¹¾åĿ¤
    0.10
    è¿ijå¹´æĿ¥
    0.09
    åįĥåı¤
    0.09
    å¤ļå¹´æĿ¥
    0.09
     reversible
    0.09
    WARDS
    0.09
    Fizz
    0.09
    è¯ĭ
    0.09
    istar
    0.09
    åīįæľŁ
    0.09
    Activations Density 0.027%

    No Known Activations