© 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. 38477
    Prev
    Next
    INDEX
    Explanations

    lists of places

    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
    ission
    -0.08
    åĪ»
    -0.08
    egal
    -0.08
    åĩ¶
    -0.08
    egl
    -0.08
    ily
    -0.08
     shielding
    -0.07
     Ñħа
    -0.07
    arth
    -0.07
    ounge
    -0.07
    POSITIVE LOGITS
    åľ°åĮºçļĦ
    0.12
    åľ°åįĢ
    0.10
    æł¡åĮº
    0.10
    缸éĤ»
    0.10
    人éĢł
    0.10
    人æ°ijæĶ¿åºľ
    0.10
    éĤ£è¾¹
    0.09
    ç¾İ丽çļĦ
    0.09
    uchen
    0.09
    èĢĢ
    0.09
    Activations Density 0.065%

    No Known Activations