© 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. 35188
    Prev
    Next
    INDEX
    Explanations

    air and its properties

    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
    翻身
    -0.11
    æ³Ĭ
    -0.10
    ä¸įæĸŃåıijå±ķ
    -0.10
    æĬĽ
    -0.10
    inker
    -0.09
    éĢĴ
    -0.09
    çĽIJ
    -0.09
    æĭ¨
    -0.09
    æĭ
    -0.09
    å¥ĭ
    -0.09
    POSITIVE LOGITS
    çĭ¡
    0.09
    бил
    0.09
    chw
    0.09
    ừa
    0.09
    é£İæľº
    0.09
    _AF
    0.08
    ssi
    0.08
    衬
    0.08
     Cand
    0.08
    kee
    0.08
    Activations Density 0.060%

    No Known Activations