© 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. 57565
    Prev
    Next
    INDEX
    Explanations

    european community unions

    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
    æĴ¬
    -0.10
    ye
    -0.10
    ç»ıå¼Ģ
    -0.09
    æĶ¯éħį
    -0.08
    éĦĻ
    -0.08
    æ¶Ĥ
    -0.08
     bor
    -0.08
    縻
    -0.08
    éĴī
    -0.08
    æĭĹ
    -0.08
    POSITIVE LOGITS
    åħ±äº«
    0.11
    ç¼Ķ
    0.10
    æĭ¢
    0.10
    æĪIJåijĺåĽ½
    0.09
    æľªæĿ¥çļĦ
    0.09
    -shared
    0.09
    åıijå±ķåīįæĻ¯
    0.09
    åĮª
    0.09
    illet
    0.09
    æī¶
    0.09
    Activations Density 0.072%

    No Known Activations