© 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. 9617
    Prev
    Next
    INDEX
    Explanations

    water runoff and drainage issues

    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
    æłĹ
    -0.11
    ç¼¢
    -0.10
    å³Ļ
    -0.10
    ä¸įå°½
    -0.10
    羸
    -0.10
    çªĴ
    -0.09
    uria
    -0.09
    æľ¬ç½ij
    -0.09
    è¾£
    -0.09
    æŁĦ
    -0.09
    POSITIVE LOGITS
    ILLE
    0.10
    管çIJĨæĿ¡ä¾ĭ
    0.09
    /english
    0.09
    reta
    0.09
    _CTL
    0.09
    opro
    0.08
    管çIJĨåĪ¶åº¦
    0.08
    APS
    0.08
    lik
    0.08
    ä¿ĿçķĻ
    0.08
    Activations Density 0.018%

    No Known Activations