© 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. 7106
    Prev
    Next
    INDEX
    Explanations

    outdoor activities and objects

    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
    天ä¸ĭ
    -0.11
    çľ¼æ³ª
    -0.10
    oad
    -0.10
     Scha
    -0.10
    TING
    -0.09
    ools
    -0.09
    etu
    -0.09
    sız
    -0.09
    -0.09
    é¡ĺ
    -0.09
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.10
    /off
    0.09
    elta
    0.09
    ebin
    0.09
    ism
    0.09
    aily
    0.08
    lle
    0.08
    WARDS
    0.08
    ists
    0.08
    /out
    0.08
    Activations Density 0.008%

    No Known Activations