© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6779
    Prev
    Next
    INDEX
    Explanations

    time and effort invested

    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
    太快
    -0.11
    ãģ¡ãĤĥ
    -0.10
    çľĭä¸Ģçľĭ
    -0.10
    廨
    -0.09
    fieldset
    -0.09
    æģ°
    -0.09
    æĢ¥éľĢ
    -0.09
    è¦ģç´§
    -0.09
    ä¸įå®Į
    -0.09
    åĬłçĽŁåºĹ
    -0.09
    POSITIVE LOGITS
    èĢĹè´¹
    0.16
    ä»ĺåĩº
    0.15
    å¿ĥè¡Ģ
    0.15
    çīºçī²
    0.12
    代价
    0.12
    èĬ±è´¹
    0.12
     effort
    0.12
    æ²¥
    0.12
    ç²¾å¿ĥ
    0.11
    è²»
    0.11
    Activations Density 0.078%

    No Known Activations