© 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. 36476
    Prev
    Next
    INDEX
    Explanations

    joint and motion conditions

    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
     Dollars
    -0.10
    плод
    -0.09
    çĦ¦
    -0.09
    éģĩ
    -0.09
    eming
    -0.09
    为ä»Ģä¹Īè¦ģ
    -0.09
    hower
    -0.09
    onis
    -0.09
    èį·
    -0.09
    åŃIJåŃĻ
    -0.09
    POSITIVE LOGITS
    éĨī
    0.09
    åĿ³
    0.09
    æ¯ı次éĥ½
    0.09
    aque
    0.09
    丰满
    0.08
    an
    0.08
     Gin
    0.08
    round
    0.08
    çŀ
    0.08
    ÑĥÑĪ
    0.08
    Activations Density 0.135%

    No Known Activations