© 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. 53496
    Prev
    Next
    INDEX
    Explanations

    United States or nation

    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
    å·¥åķĨ
    -0.10
    çIJĨå·¥
    -0.09
    åľ°å¸¦
    -0.09
    ä½ŀ
    -0.09
    åĺ´è§Ĵ
    -0.09
    æ¦Ń
    -0.09
    incare
    -0.08
    髹
    -0.08
     intim
    -0.08
    å®ļæľŁ
    -0.08
    POSITIVE LOGITS
    ocup
    0.09
    åľ¨å½ĵåľ°
    0.09
    该æĿij
    0.08
    çŃĴ
    0.08
    @student
    0.08
    ä¸Ģ段
    0.08
    æĺ¼å¤ľ
    0.08
    itur
    0.08
    uss
    0.08
     deg
    0.08
    Activations Density 0.266%

    No Known Activations