© 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. 57438
    Prev
    Next
    INDEX
    Explanations

    oceanic currents and waters

    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
    éĻĤ
    -0.10
    _tip
    -0.10
    emode
    -0.09
    çªģ
    -0.09
    çªł
    -0.09
    åħ³äºİæĪij们
    -0.09
    ç®ĢåĮĸ
    -0.09
    ç¬ijç¬ij
    -0.09
    åģļå®Į
    -0.08
    æĸ«
    -0.08
    POSITIVE LOGITS
    spo
    0.10
    温æļĸ
    0.09
    _APB
    0.09
    ijľ
    0.09
    ols
    0.09
    åħħæ²Ľ
    0.09
    ä¸įçŁ¥
    0.09
    bringing
    0.09
    routine
    0.08
    æ¶Į
    0.08
    Activations Density 0.049%

    No Known Activations