© 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. 33807
    Prev
    Next
    INDEX
    Explanations

    food and sustenance

    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
    æĪĸå°Ĩ
    -0.10
    åı¦
    -0.10
    æľįåĬ¡åĮº
    -0.09
     lượt
    -0.09
    uster
    -0.09
    pees
    -0.09
    äºĨèĩªå·±çļĦ
    -0.09
    tics
    -0.09
    avin
    -0.09
    UNC
    -0.09
    POSITIVE LOGITS
    idia
    0.08
    bero
    0.08
    é£Ĵ
    0.08
    argent
    0.08
    WithOptions
    0.08
    ÑĥпиÑĤÑĮ
    0.08
    åľ¨å®¶
    0.08
    æĿ¾
    0.07
     CPS
    0.07
     Beaver
    0.07
    Activations Density 0.019%

    No Known Activations