© 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. 20057
    Prev
    Next
    INDEX
    Explanations

    at risk

    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
    饯
    -0.09
    éĹ®ä¸ĸ
    -0.09
    æģ°æģ°
    -0.09
    dm
    -0.09
    Ĥæķ°
    -0.08
    éļĨéĩį
    -0.08
     деÑıÑĤелÑĮноÑģÑĤи
    -0.08
    åĩij
    -0.08
    å¦ĤæĦı
    -0.08
    çIJĨ
    -0.08
    POSITIVE LOGITS
     subtotal
    0.09
    åĹª
    0.09
    ngr
    0.09
    åīĮ
    0.09
    èī¯å¥½
    0.09
    è¿Ľ
    0.08
    çıī
    0.08
    è§ľ
    0.08
    ä¸ĢåĽ¢
    0.08
    峤
    0.08
    Activations Density 0.117%

    No Known Activations