© 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. 56088
    Prev
    Next
    INDEX
    Explanations

    financial expenditure and valuation

    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
    åĿĩä»·
    -0.09
    亲
    -0.09
    ç¥Ģ
    -0.09
    odem
    -0.09
    å¹³åĿĩ
    -0.09
    æĴŃ
    -0.09
     Wich
    -0.08
     dew
    -0.08
     tán
    -0.08
    _EXPECT
    -0.08
    POSITIVE LOGITS
    åıįæĺł
    0.11
    æł¸ç®Ĺ
    0.11
    æľŁæľ«
    0.10
    æĬ¥åijĬæľŁåĨħ
    0.10
    åı£å¾Ħ
    0.10
    ä¸Ģç»ı
    0.10
    åıįæĺłäºĨ
    0.10
    æĬ¥è¡¨
    0.10
    ç§ij缮
    0.09
    主管éĥ¨éŨ
    0.09
    Activations Density 0.048%

    No Known Activations