© 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. 9969
    Prev
    Next
    INDEX
    Explanations

    chromatography sample loop valve

    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
    é²ľ
    -0.12
    ileo
    -0.09
    aman
    -0.08
    ãĥĥãĥĦ
    -0.08
    è·Ħ
    -0.08
    UTH
    -0.08
    è·Į
    -0.08
     mysteries
    -0.08
    æijĨ
    -0.08
     Noon
    -0.08
    POSITIVE LOGITS
    绣
    0.09
    æīĭä¸ŃçļĦ
    0.09
    >[]
    0.09
     Slee
    0.08
    æĬ¥
    0.08
    æĭĴ
    0.08
    åįıåĬŀ
    0.08
    å«ł
    0.08
    éĵī
    0.08
    é¦ĸè½®
    0.08
    Activations Density 0.508%

    No Known Activations