© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21734
    Prev
    Next
    INDEX
    Explanations

    tolerance and intolerance

    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
    rial
    -0.11
    ellers
    -0.08
    ial
    -0.08
    人çĶŁçļĦ
    -0.08
    axe
    -0.08
    swith
    -0.08
    iers
    -0.08
    åİŁåĽłæĺ¯
    -0.08
    ogs
    -0.08
    ight
    -0.08
    POSITIVE LOGITS
    chg
    0.12
    ä¸Ģå®ļç¨ĭ度
    0.10
    cco
    0.09
    åĤ¥
    0.09
    INCLUDED
    0.09
     minded
    0.09
    ancia
    0.09
    æĢ§å¼º
    0.09
    graphics
    0.08
    çĽĹ
    0.08
    Activations Density 0.016%

    No Known Activations