© 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. 21974
    Prev
    Next
    INDEX
    Explanations

    in, on, or between things

    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
    åĶĩ
    -0.09
    æ¿Ģ
    -0.08
    å±ħ
    -0.08
    æĺ´
    -0.08
    æł·çļĦ
    -0.08
    ä¸Ńä¿Ħ
    -0.08
    ç¹ģå¿Ļ
    -0.08
    åĪº
    -0.08
    è¦ģç´ł
    -0.08
    çĶ¨èĩªå·±çļĦ
    -0.07
    POSITIVE LOGITS
    èĥ¼
    0.10
    æ²¾
    0.09
    æĥ°
    0.09
    æīª
    0.09
    letic
    0.09
    acet
    0.09
     Chapman
    0.09
    好åIJĥ
    0.08
    èĪµ
    0.08
    æĦī
    0.08
    Activations Density 0.057%

    No Known Activations