© 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. 48524
    Prev
    Next
    INDEX
    Explanations

    reach out to

    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
    ogue
    -0.09
    å°ļ书
    -0.09
    身å¿ĥåģ¥åº·
    -0.09
    mez
    -0.08
    fil
    -0.08
    æĢ»è£ģ
    -0.08
    èĹı
    -0.08
    QUIT
    -0.08
    agger
    -0.08
     Beard
    -0.08
    POSITIVE LOGITS
    伸
    0.13
    èĸª
    0.12
    伸æīĭ
    0.10
    æľĽåİ»
    0.09
    è°Ĺ
    0.09
    æݬ
    0.09
    伸åĩº
    0.09
    NETWORK
    0.09
    强åĬ²
    0.09
    æĬ¡
    0.09
    Activations Density 0.016%

    No Known Activations