© 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. 49310
    Prev
    Next
    INDEX
    Explanations

    welcome to

    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
    åłª
    -0.10
    alfa
    -0.08
    кÑĢа
    -0.08
    ãĥĢãĤ¦ãĥ³
    -0.08
     tslint
    -0.08
    éªĩ
    -0.08
    éªĪ
    -0.08
    ÑĤол
    -0.08
    hoe
    -0.07
    adget
    -0.07
    POSITIVE LOGITS
    å¾¼
    0.12
    åĨķ
    0.11
    ä»ĺè´¹
    0.10
    港澳
    0.10
    pee
    0.10
    åľ¨æ¸¸æĪıä¸Ń
    0.10
    å²Ľä¸Ĭ
    0.09
    å¨Ł
    0.09
    åľ°ä¸Ĭ
    0.09
    éĩİçĶŁ
    0.09
    Activations Density 0.008%

    No Known Activations