© 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. 50382
    Prev
    Next
    INDEX
    Explanations

    shortcut icon / command

    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
    ãģĹãģ¾ãģĨ
    -0.10
    ³
    -0.09
    åı¥è¯Ŀ
    -0.09
    åĽŀé¦ĸ
    -0.09
    helm
    -0.08
    pray
    -0.08
    å§Ķä¼ļ
    -0.08
    æľ
    -0.08
    itori
    -0.08
    ument
    -0.08
    POSITIVE LOGITS
    ../../../
    0.11
    åģ²
    0.10
    ##_
    0.10
    ãģĤãĤĭç¨ĭ度
    0.09
    ÑĢев
    0.09
    åľ°å¸¦
    0.09
    ÑĢаÑģ
    0.09
    olars
    0.09
    اش
    0.09
     dise
    0.09
    Activations Density 0.013%

    No Known Activations