© 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. 36042
    Prev
    Next
    INDEX
    Explanations

    your administrator or representative

    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
    åĬ²
    -0.08
    ç»ĻåĪ«äºº
    -0.08
    被æīĵ
    -0.08
    ä½İä¿Ŀ
    -0.08
     Liv
    -0.08
     bare
    -0.07
    _checks
    -0.07
     tre
    -0.07
    æī§çĿĢ
    -0.07
    mesh
    -0.07
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.10
    æĺ¯åIJ¦æľī
    0.10
    è£ĺ
    0.09
    äºijéĽĨ
    0.09
    姬
    0.09
    èĢ³
    0.09
    ä»ĭç»įä¸Ģä¸ĭ
    0.09
    ÙĪار
    0.09
    Paused
    0.09
    常æĢģåĮĸ
    0.09
    Activations Density 0.012%

    No Known Activations