© 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. 18241
    Prev
    Next
    INDEX
    Explanations

    working on

    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
    å±¹
    -0.09
    ä¸Ģå¤ľ
    -0.09
    nested
    -0.09
    åģļèµ·
    -0.09
    ä¸Ģè§Ĵ
    -0.09
    åĴ¤
    -0.08
    åı¯çĸij
    -0.08
    æĺ¨æĻļ
    -0.08
    çĤĴä½ľ
    -0.08
    _nested
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦ
    0.11
    umo
    0.09
    æ°´æºIJ
    0.09
     Bout
    0.08
    ä¸Ģæī¹
    0.08
    CALE
    0.08
    å¼ĢæĪ·
    0.08
    éħįå¥Ĺ设æĸ½
    0.08
     Moh
    0.08
    enberg
    0.08
    Activations Density 0.090%

    No Known Activations