© 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. 27622
    Prev
    Next
    INDEX
    Explanations

    piece of

    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
    lam
    -0.10
    iggins
    -0.10
    æĶ¶èİ·
    -0.09
    æ¹Ħ
    -0.09
    нÑĮ
    -0.09
    æľĢåIJİä¸Ģ
    -0.08
    樽
    -0.08
    æľ¬ç½ijç«Ļ
    -0.08
    CTS
    -0.08
    hare
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.13
    åħĴ
    0.12
    ars
    0.10
    ropri
    0.09
    onom
    0.09
     osc
    0.09
    å¥ł
    0.09
    æĶ¸
    0.09
    骨头
    0.09
    çīĩ
    0.08
    Activations Density 0.024%

    No Known Activations