© 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. 58858
    Prev
    Next
    INDEX
    Explanations

    choose to

    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
    ç»Ļä½łä»¬
    -0.09
     ÑģоглаÑģ
    -0.09
    婧
    -0.08
    rô
    -0.08
    æ·¡æ°´
    -0.08
     Ñģоб
    -0.08
    è¿Ļ个è¯į
    -0.08
    .Toolkit
    -0.08
     Falling
    -0.08
     Rena
    -0.07
    POSITIVE LOGITS
    å¾Ĺ太
    0.09
    游åĩ»
    0.09
    åĵªå®¶å¥½
    0.09
    èĭķ
    0.09
    äºĨä¸Ģä¸ĭ
    0.09
    产ä¸ļéĽĨèģļ
    0.09
    èĩªä¸»åĪĽæĸ°
    0.09
    ê·ł
    0.09
    ķìĿ¸
    0.09
    æ²Ķ
    0.08
    Activations Density 0.044%

    No Known Activations