© 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. 5882
    Prev
    Next
    INDEX
    Explanations

    sports and 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
    çĨ¨
    -0.10
    çݯçIJĥ
    -0.10
    éºĭ
    -0.09
    aleb
    -0.09
    åħ¸ç¤¼
    -0.09
    èĥ¥
    -0.09
    èµĽåľº
    -0.09
    ä»ĭç´¹
    -0.09
    ult
    -0.08
    è¨ĺäºĭ
    -0.08
    POSITIVE LOGITS
    æī¬
    0.10
     tennis
    0.10
    kke
    0.09
    æıļ
    0.09
    çīĮ
    0.08
    mony
    0.08
    è§ĤéŁ³
    0.08
    åħ±éĿĴ
    0.08
    eten
    0.08
    ç½ijçIJĥ
    0.08
    Activations Density 0.013%

    No Known Activations