© 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. 33751
    Prev
    Next
    INDEX
    Explanations

    preorder and order

    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
    _GE
    -0.08
    ãĥŃãĥ¼ãĥ³
    -0.08
    设计çIJĨ念
    -0.08
    æ¼Ķä¹ł
    -0.08
    褥
    -0.08
     Dias
    -0.08
    è´ŀ
    -0.08
    üt
    -0.08
    RP
    -0.08
    èİŀ
    -0.08
    POSITIVE LOGITS
    isz
    0.10
    æ½ľæ°´
    0.10
    æ´Ħ
    0.09
    chs
    0.09
    chter
    0.09
    èIJ¥åĪ©
    0.09
    รà¸Ńà¸ļ
    0.09
    æѦåĬŁ
    0.09
    ç¿»
    0.09
    åľ¨ç½ij绾
    0.09
    Activations Density 0.005%

    No Known Activations