© 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. 18472
    Prev
    Next
    INDEX
    Explanations

    Romance, legend, historical

    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
    éĻ¢å£«
    -0.09
    éĢłèĪ¹
    -0.09
    åįĥ
    -0.08
    æĺĨèĻ«
    -0.08
    endum
    -0.08
     kan
    -0.08
    æľīéĴĪ对æĢ§
    -0.08
    otron
    -0.08
     inference
    -0.08
    æľīåĪ©
    -0.08
    POSITIVE LOGITS
    å°ijå¹´
    0.10
     Wilde
    0.10
    ä¸Ģé¢Ĺ
    0.10
    æīĭå¥Ĺ
    0.09
    æ´ģçĻ½
    0.09
    ç½Ķ
    0.09
    çĻ½äºij
    0.09
    éĩijéĵ¶
    0.09
    ç²¾ç¾İ
    0.09
    åĩłå¤©
    0.09
    Activations Density 0.045%

    No Known Activations