© 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. 35122
    Prev
    Next
    INDEX
    Explanations

    perceptual, conceptual, world

    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
     dest
    -0.08
     Dest
    -0.08
    _unc
    -0.08
    çİij
    -0.08
    çµ®
    -0.08
    UN
    -0.08
    è¿«
    -0.07
    å¸Ĥéķ¿
    -0.07
    è´ª
    -0.07
     callee
    -0.07
    POSITIVE LOGITS
    äºĶå®ĺ
    0.10
    空åīį
    0.10
    鼷éľĨ
    0.10
    缴æİ¥
    0.09
    åĴĮ社ä¼ļ
    0.09
    Atom
    0.09
    _UNUSED
    0.09
    缮ãģ®
    0.09
    å¤ĸéĿ¢
    0.09
    ë°ĸ
    0.09
    Activations Density 0.050%

    No Known Activations