© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    value or values

    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
    ä¸Ńä¿Ħ
    -0.09
    é£ŀèĪ¹
    -0.08
     Tyson
    -0.08
    åĮħ容
    -0.08
    essed
    -0.08
    åĸij
    -0.08
    æĹłéļľç¢į
    -0.08
    ilden
    -0.08
    æµģçķħ
    -0.08
    é£İæĥħ
    -0.08
    POSITIVE LOGITS
    åĢ¼
    0.20
     values
    0.16
    ê°Ĵ
    0.16
     value
    0.16
     ê°Ĵ
    0.14
     ê°ĴìĿĦ
    0.14
    æķ°åĢ¼
    0.13
     Values
    0.13
     знаÑĩение
    0.13
    _VALUE
    0.12
    Activations Density 0.932%

    No Known Activations