© 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. 51267
    Prev
    Next
    INDEX
    Explanations

    patch or patches

    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
    inand
    -0.10
    æĸ¯å¡Ķ
    -0.10
    ischer
    -0.09
    apo
    -0.09
    ight
    -0.09
    .setLocation
    -0.08
    æ½®
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    ãģĹãģ¦ãģĬãĤĬ
    -0.08
    å®Įæ¯ķ
    -0.08
    POSITIVE LOGITS
    修补
    0.10
     TECH
    0.09
    ily
    0.09
    æĪ¿åŃIJ
    0.09
    åħĴ
    0.08
     pockets
    0.08
    èģĬèģĬ
    0.08
    æŀ°
    0.08
    绣
    0.08
    quirer
    0.08
    Activations Density 0.014%

    No Known Activations