© 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. 18560
    Prev
    Next
    INDEX
    Explanations

    posting personal details

    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
    表çİ°
    -0.09
    alias
    -0.09
    æĢ¯
    -0.09
     окÑĢÑĥг
    -0.08
    åĩºäºİ
    -0.08
    æĵ¢
    -0.08
    çĪª
    -0.08
    åĪĨå±Ģ
    -0.08
    æݩ饰
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
    POSITIVE LOGITS
    öffentlich
    0.09
    èĽŃ
    0.09
    注å®ļ
    0.09
    èĮ«
    0.09
    æĮĩçĤ¹
    0.08
    éĥ¨åĪĨ
    0.08
    åĪĿå¿ĥ
    0.08
     ÐijеÑģ
    0.08
    çł´
    0.08
     полÑĮз
    0.08
    Activations Density 0.064%

    No Known Activations