© 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. 59049
    Prev
    Next
    INDEX
    Explanations

    recent updates

    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
    å±ĬæŶ
    -0.13
    å½ĵå¹´
    -0.13
    å½ĵæŶ
    -0.12
    æĹ¥åIJİ
    -0.12
    ä¸Ģå¼Ģå§ĭå°±
    -0.12
    å½ĵåĪĿ
    -0.12
    æĹ©åľ¨
    -0.11
    æ°¸è¿ľä¸įä¼ļ
    -0.11
    æĹ©å°±
    -0.11
    ä¸Ģå¼Ģå§ĭ
    -0.11
    POSITIVE LOGITS
    çĥŃæĴŃ
    0.09
    ÙĦÙĬ
    0.09
    empt
    0.09
    æ°´éĿ¢
    0.09
    Conv
    0.08
    åĩºçĤī
    0.08
    宣å¸ĥ
    0.08
    quisitions
    0.08
    åĩłæ¬¡
    0.08
    åIJ¯çĶ¨
    0.08
    Activations Density 0.147%

    No Known Activations