© 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. 21814
    Prev
    Next
    INDEX
    Explanations

    availability and vacancies

    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
    åı¦ä¸Ģ个
    -0.08
    ill
    -0.08
    aud
    -0.08
    åģļ强
    -0.08
    ä¸Ĭæ¦ľ
    -0.08
    ä¹Łæĺ¯ä¸Ģ个
    -0.08
    为客æĪ·
    -0.07
    å½ĵæŶ
    -0.07
     another
    -0.07
    orting
    -0.07
    POSITIVE LOGITS
    ä¸Ģèµ·åİ»
    0.10
    éģĹ
    0.10
    è´¹çĶ¨
    0.09
    çĸ±
    0.09
    éħ¬
    0.09
     полÑĥÑĩен
    0.09
    lâ
    0.09
    æģ¶
    0.09
    ä¸Ģèµ·æĿ¥
    0.09
    Marsh
    0.09
    Activations Density 0.067%

    No Known Activations