© 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. 53655
    Prev
    Next
    INDEX
    Explanations

    dosage and quantity units

    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
    第ä¸Ģä½į
    -0.10
    çªģ
    -0.09
    åľ¨è¿Ļ
    -0.09
    éļİ
    -0.09
     PROGMEM
    -0.09
    å½ķ
    -0.08
     Hal
    -0.08
    çĤ¹äºĨ
    -0.08
    ä¸Ģ个个
    -0.08
    ä¸įä¹ı
    -0.08
    POSITIVE LOGITS
    åį³åı¯
    0.09
    æĪĸå¤ļ
    0.08
     tod
    0.08
    ç«ŀ
    0.08
    ä¸ĭéĿ¢å°±
    0.08
    å°ıäºĭ
    0.08
    èļ¬
    0.08
    anie
    0.08
    .AutoScaleMode
    0.08
    åĮĻ
    0.08
    Activations Density 0.049%

    No Known Activations