© 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. 21482
    Prev
    Next
    INDEX
    Explanations

    film feature

    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
    heid
    -0.10
    æŁ¥å¤Ħ
    -0.08
    emy
    -0.08
    ãģ»ãģĨãģĮ
    -0.08
    亲
    -0.08
    ä¹ł
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
    æ´ĹèĦ¸
    -0.08
    ÑĦи
    -0.08
    æ§ģ
    -0.08
    POSITIVE LOGITS
    tte
    0.10
    yro
    0.10
    ä¸įå®Į
    0.09
    ableObject
    0.09
    عÙĦÙī
    0.09
    aceous
    0.09
    /math
    0.09
    åŁ
    0.09
    hest
    0.09
    å¤ł
    0.09
    Activations Density 0.016%

    No Known Activations