© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    issues of claim preclusion

    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
     Dame
    -0.09
    CEE
    -0.09
     Ñģобой
    -0.09
    Iso
    -0.09
    kad
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    æĭ¦æĪª
    -0.09
    ä»ĭç»įä¸Ģä¸ĭ
    -0.08
    æ°ijçĶ¨
    -0.08
    夸大
    -0.08
    POSITIVE LOGITS
    æѤå¤Ħ
    0.09
    atu
    0.09
    仪
    0.08
    涧
    0.08
    FromFile
    0.08
     Ster
    0.08
    亢
    0.08
    æĹ¢æĺ¯
    0.08
    端æŃ£
    0.07
    é»į
    0.07
    Activations Density 0.010%

    No Known Activations