© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    ground floor or first floor

    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
    éĵ¼
    -0.09
    箧
    -0.08
    桤
    -0.08
     Äijứng
    -0.08
    çļĦè¯Ŀ
    -0.08
    (nc
    -0.08
    astically
    -0.08
    .stride
    -0.08
    ä¸Ģ棵
    -0.08
    foon
    -0.08
    POSITIVE LOGITS
    楼å±Ĥ
    0.11
    顶å±Ĥ
    0.10
    楼ä¸Ĭ
    0.10
     level
    0.10
    ä¸Ģå±Ĥ
    0.09
     Crane
    0.09
    å¾Ģä¸Ĭ
    0.09
    ä¸Ģ楼
    0.09
    ground
    0.09
    igi
    0.08
    Activations Density 0.097%

    No Known Activations