© 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. 57540
    Prev
    Next
    INDEX
    Explanations

    fill in forms or data

    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
    深深çļĦ
    -0.09
    è¶Ĭ
    -0.09
    Ñģлов
    -0.09
    _overlap
    -0.08
    burger
    -0.08
    oran
    -0.08
    åIJijå¾Ģ
    -0.08
    æĺİæĺİ
    -0.08
     waves
    -0.08
    лÑİÑĩ
    -0.08
    POSITIVE LOGITS
    äºĽ
    0.11
    对èĩªå·±çļĦ
    0.09
    enses
    0.09
    缸è¯Ĩ
    0.09
    _own
    0.09
    æŀĿ
    0.09
    ä¸įä¸ĭ
    0.09
    çĩŁ
    0.09
    å¹´é¾Ħ段
    0.09
    stash
    0.09
    Activations Density 0.009%

    No Known Activations