© 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. 52691
    Prev
    Next
    INDEX
    Explanations

    copyright symbol

    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
    ington
    -0.08
    ç»ķ
    -0.08
    oud
    -0.08
    ase
    -0.08
    ä¸ŃåĽ½æ¢¦
    -0.08
    ä»ĭ
    -0.08
    巴西
    -0.07
     Cristiano
    -0.07
    åĪĨæľŁ
    -0.07
    chia
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.17
    ï¸
    0.13
    nds
    0.10
    สà¸ĩ
    0.10
     weekday
    0.10
    opyright
    0.09
    è¨ĺèĢħ
    0.09
    åģ»
    0.09
    _SZ
    0.09
    æѤåĪ»
    0.09
    Activations Density 0.034%

    No Known Activations