© 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. 61846
    Prev
    Next
    INDEX
    Explanations

    own [noun]

    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
    ally
    -0.08
    æĺİæĻº
    -0.08
     unint
    -0.08
    çī¹æĦı
    -0.08
     Wallpaper
    -0.08
    ovsky
    -0.07
    wise
    -0.07
    ully
    -0.07
    ops
    -0.07
    embr
    -0.07
    POSITIVE LOGITS
    佶
    0.10
    éĤ¸
    0.10
    _FLAG
    0.09
    orro
    0.09
    VERT
    0.09
    gef
    0.09
    afx
    0.09
    ddy
    0.09
    .market
    0.09
    court
    0.09
    Activations Density 0.028%

    No Known Activations