© 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. 57127
    Prev
    Next
    INDEX
    Explanations

    space

    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
    èķĪ
    -0.11
    ä¸Ģåľº
    -0.11
    æķĪçĽĬ
    -0.10
    abus
    -0.09
    ä¸įä¹ħ
    -0.09
     Rut
    -0.08
    å¤ļå°ijéĴ±
    -0.08
    å°ıèħ¿
    -0.08
    ä¸Ģæł¹
    -0.08
    é¢Ĩ
    -0.08
    POSITIVE LOGITS
    ä¹Łå¥½
    0.09
    缸åħ³åĨħ容
    0.09
    gra
    0.09
    ä¹ĸä¹ĸ
    0.09
    asing
    0.08
    xac
    0.08
    gow
    0.08
    itting
    0.08
    为主è¦ģ
    0.08
    åķª
    0.08
    Activations Density 0.034%

    No Known Activations