© 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. 2811
    Prev
    Next
    INDEX
    Explanations

    superb or splendid

    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
    gable
    -0.11
    ional
    -0.10
    opies
    -0.08
    ãģĻãģIJãģ«
    -0.08
    以ä¾Ĩ
    -0.08
    abouts
    -0.08
    osed
    -0.08
    obbled
    -0.08
    ç²Ĺ
    -0.08
    eras
    -0.07
    POSITIVE LOGITS
    ly
    0.15
     nét
    0.10
    ment
    0.10
    æĺĻ
    0.10
    窿
    0.10
    è¹Ĥ
    0.10
    loom
    0.10
    ously
    0.10
    èĭij
    0.10
    rio
    0.09
    Activations Density 0.006%

    No Known Activations