© 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. 18908
    Prev
    Next
    INDEX
    Explanations

    addresses and contact information

    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
    1
    -0.09
    9
    -0.09
    åĩºè·¯
    -0.09
    ial
    -0.08
    ogr
    -0.08
    é£Ľãģ³
    -0.08
    è¿Ļ个è¯į
    -0.08
    æĿŃ
    -0.08
    æijĶ
    -0.08
    ante
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.10
    à¸Ĺะ
    0.09
    å¼ij
    0.09
     Nicol
    0.09
    upakan
    0.09
    æ£ł
    0.09
    RuntimeObject
    0.09
    ðŁĵŀ
    0.09
    诱导
    0.09
    templ
    0.09
    Activations Density 0.029%

    No Known Activations