© 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. 61315
    Prev
    Next
    INDEX
    Explanations

    VAT and tax

    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
    éĥİ
    -0.09
    诱åıij
    -0.09
    hood
    -0.08
    çĸĹæ³ķ
    -0.08
     nas
    -0.08
    åĤ©
    -0.08
    ry
    -0.08
    诳
    -0.08
    é¢ĦæĬ¥
    -0.08
    ining
    -0.08
    POSITIVE LOGITS
    ugh
    0.10
    åĴĮ个人
    0.10
    çīį
    0.09
    éĩĮæĸ¯
    0.09
     mell
    0.09
    éĩľ
    0.09
    acin
    0.08
    UGH
    0.08
    å°ıäºĭ
    0.08
    è¿ľæĸ¹
    0.08
    Activations Density 0.005%

    No Known Activations