© 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. 7068
    Prev
    Next
    INDEX
    Explanations

    names and affiliations

    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
    æij¸
    -0.09
    éĵº
    -0.08
    娱
    -0.08
     СеÑĢгей
    -0.08
    ouch
    -0.08
    èĴ²
    -0.08
    Wer
    -0.08
    abit
    -0.08
    mers
    -0.08
    isten
    -0.08
    POSITIVE LOGITS
    å®īå¨ľ
    0.09
    裹
    0.09
    æĬĹéľĩ
    0.09
     há»ĵi
    0.08
    beat
    0.08
    ustum
    0.08
    -community
    0.08
    æµ·æ´ĭ
    0.08
    finder
    0.08
     ÑĥÑģпеÑĪ
    0.08
    Activations Density 0.071%

    No Known Activations