© 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. 35631
    Prev
    Next
    INDEX
    Explanations

    Germanic-sounding names or suffixes

    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
    ãģıãģłãģķãģĦ
    -0.10
    ãģıãĤĮ
    -0.10
     лиÑĪÑĮ
    -0.10
    chrono
    -0.09
    clang
    -0.09
    sect
    -0.09
    ãģĬãĤĬ
    -0.09
    heed
    -0.09
    ikk
    -0.09
    aris
    -0.09
    POSITIVE LOGITS
    allenge
    0.15
    ãĥ§ãĥ³
    0.14
    ãĥ£
    0.14
    itecture
    0.14
    ttp
    0.13
    eshire
    0.13
    ãĤħ
    0.12
    ieved
    0.12
    andler
    0.12
    á»ĵng
    0.12
    Activations Density 0.197%

    No Known Activations