© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52806
    Prev
    Next
    INDEX
    Explanations

    sports and news updates

    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
    åħħè£ķ
    -0.09
    çĹķ迹
    -0.09
    两级
    -0.08
    æ¶ĪçģŃ
    -0.08
    owitz
    -0.08
    edReader
    -0.08
    马æĿ¥
    -0.08
    è§ħ
    -0.08
    èľĹ
    -0.08
    èĭ¦
    -0.08
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.12
     sports
    0.09
    ÑģпоÑĢ
    0.09
    è¿IJåĬ¨åijĺ
    0.09
    Sports
    0.09
     ESPN
    0.09
    sports
    0.09
    åĻ¨æĿIJ
    0.09
    Ùģا
    0.08
    设æĸ½
    0.08
    Activations Density 0.058%

    No Known Activations