© 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. 61427
    Prev
    Next
    INDEX
    Explanations

    lazy loading and evaluation

    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
     Ont
    -0.09
    çĿ¦
    -0.09
    çłĶ究éĻ¢
    -0.09
    é²µ
    -0.09
    榷
    -0.09
    ãĥŃãĥĥãĤ¯
    -0.09
     bó
    -0.09
    GEST
    -0.09
    fare
    -0.09
    ÑĢаб
    -0.09
    POSITIVE LOGITS
    æĩĴ
    0.33
    æĥ°
    0.26
     lazy
    0.25
    .lazy
    0.23
    lazy
    0.21
     laz
    0.21
     Lazy
    0.20
    Lazy
    0.20
    æħµ
    0.20
    æĩĴå¾Ĺ
    0.19
    Activations Density 0.060%

    No Known Activations