© 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. 48363
    Prev
    Next
    INDEX
    Explanations

    playing sports or games

    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
    åģļæ³ķ
    -0.10
    ChartData
    -0.10
    åģļå¾Ĺ
    -0.09
    corn
    -0.09
    溲
    -0.09
    à¸ģระà¸Ĺ
    -0.09
    hold
    -0.09
    ä¸Ģç»Ħ
    -0.09
    idad
    -0.08
    ä¸Ģ大æī¹
    -0.08
    POSITIVE LOGITS
    éģı
    0.10
    aille
    0.10
    äºĽä»Ģä¹Ī
    0.10
    offs
    0.09
    åħ¶æīĢ
    0.09
    -offs
    0.08
    isci
    0.08
    ook
    0.08
    è¿ĩçļĦ
    0.08
    ied
    0.08
    Activations Density 0.048%

    No Known Activations