© 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. 52425
    Prev
    Next
    INDEX
    Explanations

    interpolation operators

    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
    tha
    -0.08
    æĺĤ
    -0.08
    è·¯éĿ¢
    -0.08
     Gast
    -0.08
    éĹª
    -0.08
    ç²¾åįİ
    -0.07
    eland
    -0.07
    pard
    -0.07
    werk
    -0.07
    .serialization
    -0.07
    POSITIVE LOGITS
    IndexOf
    0.10
    ä¸ĢéĿ¢
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    âģ½
    0.09
    è£ħéħį
    0.08
     Feinstein
    0.08
    éĹ´éļĶ
    0.08
    à¸ķà¸ģ
    0.08
    æľ¬æľŁ
    0.08
    æİĴæ°Ķ
    0.08
    Activations Density 0.718%

    No Known Activations