© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    celebrity and artist names

    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
    اÙħا
    -0.09
    éĤ£å¤©
    -0.09
    综
    -0.09
    inals
    -0.09
    æ¸ħé¦Ļ
    -0.09
    дол
    -0.09
    geist
    -0.09
    éļIJéļIJ
    -0.08
    å¦
    -0.08
    bolt
    -0.08
    POSITIVE LOGITS
    æ¯įæł¡
    0.09
    亲èĩª
    0.09
    è¯ĺ
    0.09
    æħĪåĸĦ
    0.09
    irst
    0.08
    haus
    0.08
    /generated
    0.08
    å¼¼
    0.08
    æī¹è¯Ħ
    0.08
    çķĻ
    0.08
    Activations Density 0.124%

    No Known Activations