© 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. 48619
    Prev
    Next
    INDEX
    Explanations

    article and noun grammar

    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
     Herc
    -0.09
    ploy
    -0.09
     Weber
    -0.09
     fac
    -0.08
    ifest
    -0.08
     Wid
    -0.08
    vet
    -0.08
    èĥŀ
    -0.08
    _HANDLE
    -0.08
     Syndrome
    -0.08
    POSITIVE LOGITS
    è¯Ńæ°Ķ
    0.10
    åī¯
    0.10
    æĤ¬
    0.10
     Gratuit
    0.09
    åĪº
    0.09
    ìŀ¥ìĿĦ
    0.09
     determin
    0.09
     animate
    0.09
    é¢Ĩè¡Ķ
    0.09
    ä»ĭ
    0.09
    Activations Density 0.108%

    No Known Activations