© 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. 37648
    Prev
    Next
    INDEX
    Explanations

    is governed by or subject to

    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
    è¡¢
    -0.09
    æݨçIJĨ
    -0.09
    å¿ĥæĢĿ
    -0.09
    eon
    -0.09
    æĶ¶çº³
    -0.09
    ogue
    -0.09
    沿éĢĶ
    -0.09
     Literature
    -0.09
    empt
    -0.09
    è§ij
    -0.09
    POSITIVE LOGITS
    ä¼ļç»Ļ
    0.09
    æ£Ģ
    0.08
    å¾ģæ±Ĥ
    0.08
    æ·¤
    0.08
    éĢł
    0.08
    çĿģ
    0.08
    èµ·æĿ¥
    0.08
    ross
    0.08
    çIJ¬
    0.08
    Symfony
    0.08
    Activations Density 0.016%

    No Known Activations