© 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. 30888
    Prev
    Next
    INDEX
    Explanations

    family history

    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
    RIX
    -0.09
    åķĨä¸ļåĮĸ
    -0.09
    idel
    -0.09
    åĸľ
    -0.09
    eder
    -0.08
     Elder
    -0.08
    å¸ĤåľºåĮĸ
    -0.08
    çľĭä¸įè§ģ
    -0.08
    人çĶŁ
    -0.08
    çĿĢçľ¼äºİ
    -0.08
    POSITIVE LOGITS
    éģĹä¼ł
    0.13
    家æĹı
    0.11
    ç¥ĸåħĪ
    0.10
    åĢ¾åIJij
    0.09
    ä¿İ
    0.09
    大çIJĨçŁ³
    0.09
    åħ¸åŀĭ
    0.09
    亲æĪļ
    0.09
    箩
    0.08
    亲人
    0.08
    Activations Density 0.119%

    No Known Activations