© 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. 50777
    Prev
    Next
    INDEX
    Explanations

    hard working and difficult situations

    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
    漫
    -0.08
     поÑģледние
    -0.08
    åIJĮä¸ļ
    -0.08
    容
    -0.08
    é¢ĸ
    -0.08
     pé
    -0.08
    容éĩı
    -0.08
     Cro
    -0.08
    æĻ°
    -0.08
    褰
    -0.08
    POSITIVE LOGITS
    _hard
    0.10
     hard
    0.10
    èĩªèIJ¥
    0.10
    hard
    0.10
    çĸ¾
    0.10
    èĢIJçĶ¨
    0.10
     Hard
    0.10
    -hard
    0.10
    ä¸į解
    0.09
    æ¡¢
    0.09
    Activations Density 0.011%

    No Known Activations