© 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. 2148
    Prev
    Next
    INDEX
    Explanations

    becomes clear or realizes that

    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
    çİ°åľ¨
    -0.12
    ä»İæѤ
    -0.12
    å±ĬæŶ
    -0.12
    ä½łçİ°åľ¨
    -0.12
    è¿Ļæīį
    -0.12
    èĩ³ä»Ĭ
    -0.11
     now
    -0.11
    ä¸Ģç»ı
    -0.11
    è¿Ħä»Ĭ
    -0.11
     ÑģейÑĩаÑģ
    -0.10
    POSITIVE LOGITS
    rox
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    _Impl
    0.09
    ants
    0.09
    äºĨ解åĪ°
    0.09
    åķ¬
    0.08
    åķª
    0.08
    建ç«ĭèµ·
    0.08
     enough
    0.08
    alis
    0.08
    Activations Density 0.057%

    No Known Activations