© 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. 26536
    Prev
    Next
    INDEX
    Explanations

    AAD

    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
    ç¬ı
    -0.10
     Vinci
    -0.09
    å®ļåIJij
    -0.08
    夷
    -0.08
    诰
    -0.08
    è°ĥåīĤ
    -0.08
    çļĦä¸ĵä¸ļ
    -0.08
    rale
    -0.08
    æī¹ç¤º
    -0.08
    ÙĪع
    -0.08
    POSITIVE LOGITS
    éĢ¼
    0.10
    _EPS
    0.10
    ections
    0.10
    bish
    0.09
    çĿ¹
    0.09
    æ°´æĻ¶
    0.09
     ÑĥнивеÑĢÑģ
    0.09
    èĮķ
    0.09
    enha
    0.09
    éķ¿åŁİ
    0.09
    Activations Density 0.002%

    No Known Activations