© 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. 37611
    Prev
    Next
    INDEX
    Explanations

    flowers and blooms

    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
    é²²
    -0.10
    åIJĥé¥Ń
    -0.10
    rect
    -0.09
    轸
    -0.09
    Rect
    -0.09
    éĢ®
    -0.09
    rch
    -0.09
     rect
    -0.09
    åĮķ
    -0.09
    潺
    -0.08
    POSITIVE LOGITS
    ä¸Ģæľµ
    0.20
    缼å¼Ģ
    0.18
    èĬ±æľµ
    0.17
    é²ľèĬ±
    0.17
     flowers
    0.17
    èĬ±
    0.17
    èĬ±å¼Ģ
    0.16
     Flowers
    0.15
     blooms
    0.15
     flower
    0.14
    Activations Density 0.078%

    No Known Activations