© 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. 5562
    Prev
    Next
    INDEX
    Explanations

    game specific terms

    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
    夫
    -0.10
    ollen
    -0.09
    ukes
    -0.09
    IME
    -0.09
    缴å±ŀ
    -0.08
    ãĥ«ãĥ¼
    -0.08
    yre
    -0.08
     å½
    -0.08
    夫å¦ĩ
    -0.08
    润æ»ij
    -0.08
    POSITIVE LOGITS
    çī©ä¸ļæľįåĬ¡
    0.09
    çī©ä¸ļ管çIJĨ
    0.09
    åĪ°å¤Ħ
    0.08
    åŃ³
    0.08
    æijĺ
    0.08
    æѦåĻ¨
    0.08
    çĤĬ
    0.08
    æ¼³
    0.08
    bia
    0.08
    éĽ¾
    0.08
    Activations Density 0.131%

    No Known Activations