© 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. 48553
    Prev
    Next
    INDEX
    Explanations

    minutes and days

    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
    èĻ¹
    -0.10
    uat
    -0.10
    ÑĤÑĢо
    -0.09
    ожеÑĤ
    -0.09
    åİĨåı²æĤłä¹ħ
    -0.09
    è´µ
    -0.09
    зи
    -0.09
    使åħ¶
    -0.09
    ban
    -0.08
    ukes
    -0.08
    POSITIVE LOGITS
    å½ĺ
    0.09
    人å±ħ
    0.09
    ä»ĭ
    0.09
    åªĴ
    0.09
    Pure
    0.09
    纯
    0.09
    _wp
    0.09
     ath
    0.08
    æ¼Ķ
    0.08
    èĩªåľ¨
    0.08
    Activations Density 0.115%

    No Known Activations