© 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. 52746
    Prev
    Next
    INDEX
    Explanations

    essays and creative writing

    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
     Dep
    -0.10
    ipped
    -0.10
    èĢĥè¯ģ
    -0.09
    Ship
    -0.09
    夯å®ŀ
    -0.09
    ç¿ĺ
    -0.09
    æĵ
    -0.08
     proto
    -0.08
    串
    -0.08
    coded
    -0.08
    POSITIVE LOGITS
    ä½ľæĸĩ
    0.18
    åĨĻä½ľ
    0.15
     essays
    0.13
     writing
    0.12
     Writing
    0.12
     essay
    0.11
     Write
    0.11
    åĨĻåĩº
    0.11
    .Write
    0.11
    Writing
    0.11
    Activations Density 0.096%

    No Known Activations