© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51929
    Prev
    Next
    INDEX
    Explanations

    difficulties getting conference wins

    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
    ÑģеÑĤ
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
    寻
    -0.09
    éĿ©
    -0.08
    羣å®ŀæĢ§
    -0.08
    paired
    -0.08
     Caller
    -0.08
    æī°ä¹±
    -0.08
    æĸ°è¥¿
    -0.08
    éĥľ
    -0.08
    POSITIVE LOGITS
    说æľį
    0.11
    人å¿ĥ
    0.11
    çļĦåIJĪä½ľ
    0.10
    æĦ¿æĦı
    0.10
    对æĸ¹
    0.10
    olla
    0.10
    ä¹IJæĦı
    0.09
     reluctant
    0.09
     Bibli
    0.09
    å°įæĸ¹
    0.09
    Activations Density 0.118%

    No Known Activations