© 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. 31102
    Prev
    Next
    INDEX
    Explanations

    awk command

    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
    æľº
    -0.10
    loth
    -0.09
    èĺ¸
    -0.09
     наÑħодиÑĤÑģÑı
    -0.08
    oload
    -0.08
    ingroup
    -0.08
    æĶĴ
    -0.08
    endency
    -0.08
    éĵħ
    -0.08
     stain
    -0.08
    POSITIVE LOGITS
    inaire
    0.09
    缴éĶĢ
    0.08
    çļĦçľ¼ç¥ŀ
    0.08
    kdir
    0.08
    èľĪ
    0.08
    lique
    0.08
    éĿ¢åŃIJ
    0.08
    å¼ŁåħĦ
    0.07
    odox
    0.07
    .Fail
    0.07
    Activations Density 0.004%

    No Known Activations