© 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. 31508
    Prev
    Next
    INDEX
    Explanations

    game series scores

    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
    ä»ķ
    -0.10
    ä¸Ģä½ĵ
    -0.09
    ral
    -0.09
     labs
    -0.09
    è¿ľæĻ¯
    -0.09
    spl
    -0.09
    æ°ı
    -0.08
    èĩªå¾ĭ
    -0.08
    åģļæ³ķ
    -0.08
    ä¿Ŀåħ»
    -0.08
    POSITIVE LOGITS
    åĨ³èĥľ
    0.10
    åĨ³èµĽ
    0.09
    ç³»åĪĹ
    0.09
     mạch
    0.09
    æĢ»åĨ³èµĽ
    0.09
    çİł
    0.09
     Má
    0.09
    ÑĤик
    0.08
    .clients
    0.08
    Fixture
    0.08
    Activations Density 0.083%

    No Known Activations