© 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. 31328
    Prev
    Next
    INDEX
    Explanations

    float, floating, flotation

    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
    èŀ«
    -0.10
    åľ°ä¸ĭ室
    -0.10
    ifr
    -0.10
    åľ°ä¸ĭ
    -0.09
    ihar
    -0.09
    MEA
    -0.09
    oldem
    -0.09
    ä¸įæĸŃæıIJé«ĺ
    -0.09
    iams
    -0.09
    å¹²åĩĢ
    -0.09
    POSITIVE LOGITS
    æ¼Ĥæµģ
    0.13
    æ¼Ĥ
    0.10
    æµ®
    0.10
    çŃı
    0.09
    éĺħ
    0.09
    åĿIJ
    0.09
    èĪ¸
    0.09
     Float
    0.09
    åħ¥å¢ĥ
    0.09
     Floating
    0.09
    Activations Density 0.100%

    No Known Activations