© 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. 30462
    Prev
    Next
    INDEX
    Explanations

    character, integrity, ethics

    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
     perk
    -0.10
    忽
    -0.09
    æ°Ķæ°Ľ
    -0.09
    rimp
    -0.09
    æĸ©
    -0.09
    ook
    -0.09
    é£
    -0.09
    åħļåĨħ
    -0.08
    å¤ļ彩
    -0.08
     Cheer
    -0.08
    POSITIVE LOGITS
    åģļ人
    0.10
    èĩªå¾ĭ
    0.10
    иÑĪ
    0.10
    è¯ļä¿¡
    0.09
    åĵģæł¼
    0.09
    éĴ»çŁ³
    0.09
    å½ĺ
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
    åĵģ
    0.09
    .Emit
    0.08
    Activations Density 0.014%

    No Known Activations