© 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. 57882
    Prev
    Next
    INDEX
    Explanations

    confidential information and details

    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
    æĪ¾
    -0.10
    æĪIJåIJį
    -0.09
    çļĦ身份
    -0.09
     Identity
    -0.08
    主ä½ĵ
    -0.08
     bucks
    -0.08
    ãģ«åIJij
    -0.08
    èĥ±
    -0.08
    Identity
    -0.08
    çĸı
    -0.08
    POSITIVE LOGITS
    æĭ¿æĿ¥
    0.09
    enta
    0.09
    ä¸ºæł¸å¿ĥçļĦ
    0.09
    京
    0.09
    åĪĨä¼ļ
    0.08
    被çĽĹ
    0.08
    _kel
    0.08
    çī§åľº
    0.08
    RFC
    0.08
    ight
    0.08
    Activations Density 0.057%

    No Known Activations