© 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. 18185
    Prev
    Next
    INDEX
    Explanations

    remember when you

    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
    å¹Į
    -0.10
    å·¨åŀĭ
    -0.10
    iais
    -0.10
    åı²ä¸ĬæľĢ
    -0.09
    è°ĭ
    -0.09
     пÑĢид
    -0.09
     ëıĦ
    -0.09
    åĢĴæĺ¯
    -0.09
    ä¸Ĭè°ĥ
    -0.09
    åĪĨæīĭ
    -0.09
    POSITIVE LOGITS
    æĪļ
    0.08
     LU
    0.08
    ä¹ĭæĦı
    0.08
    تس
    0.08
     Pes
    0.08
    _BB
    0.08
    强çĥĪçļĦ
    0.08
    arden
    0.08
    ordan
    0.08
     Ble
    0.08
    Activations Density 0.015%

    No Known Activations