© 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. 23185
    Prev
    Next
    INDEX
    Explanations

    human evolution and ancient people

    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
    æħİ
    -0.10
    å¿į
    -0.09
    æĿ¥åģļ
    -0.09
    uhan
    -0.09
     bic
    -0.09
    åĴĦ
    -0.08
     воÑģ
    -0.08
    é²ľæ´»
    -0.08
    /of
    -0.08
    æŃ£å¸¸
    -0.08
    POSITIVE LOGITS
    鼩
    0.10
    çļĦæ¯į亲
    0.09
    ä¹Įé²ģ
    0.09
    æľĹ
    0.09
    æľīäºĨ
    0.09
    .generator
    0.09
    åħ±åĪĽ
    0.08
    æŃĥ
    0.08
     Vere
    0.08
    _INTR
    0.08
    Activations Density 0.029%

    No Known Activations