© 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. 11583
    Prev
    Next
    INDEX
    Explanations

    Al-Thani bin Jassim bin Jaber

    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
    éĶģ
    -0.09
    é«ĺéĢŁ
    -0.09
    笥
    -0.09
    æĴ©
    -0.09
     Tahoe
    -0.09
    riad
    -0.08
    æĭĪ
    -0.08
    esz
    -0.08
    å¨ģ
    -0.08
    æīĴ
    -0.08
    POSITIVE LOGITS
    符åIJĪ
    0.09
    èĩ»
    0.08
    ä¸ĩåįĥ
    0.08
    -twitter
    0.08
    ä¸ĢæŃ¥
    0.08
    รา
    0.08
    ä½ĵè´¨
    0.08
    ä¸ľæµ·
    0.08
    /animations
    0.08
    ä¸Ģ个人
    0.08
    Activations Density 0.030%

    No Known Activations