© 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. 37895
    Prev
    Next
    INDEX
    Explanations

    between ... and

    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
    亲åĪĩ
    -0.10
    Touches
    -0.09
    æĭĸ
    -0.09
    å¡ĺ
    -0.09
    åĨħå¤ĸ
    -0.09
    帮
    -0.09
    ä¸į满
    -0.09
    åħļæĢ»
    -0.08
    å·§
    -0.08
    é¢į
    -0.08
    POSITIVE LOGITS
    ä¹ĭéĹ´çļĦ
    0.10
     междÑĥ
    0.10
     Companion
    0.10
    è¿Ļ段æŶéĹ´
    0.10
     between
    0.10
    éľĦ
    0.09
    èĥ´
    0.09
    é¤IJæ¡Į
    0.09
     giữa
    0.09
    çŀ¬
    0.09
    Activations Density 0.067%

    No Known Activations