© 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. 38900
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and position

    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
    æ®·
    -0.10
    PTY
    -0.08
    tab
    -0.08
    äºĮç»´
    -0.08
    åģĥ
    -0.08
     Verb
    -0.08
    åħīè¾ī
    -0.08
    èĤĩ
    -0.08
    tw
    -0.08
     Orleans
    -0.08
    POSITIVE LOGITS
    éĢļè¡Į
    0.11
    å¢ŀ设
    0.09
    errick
    0.09
    .Typed
    0.09
    欲
    0.09
    èįª
    0.09
    寮
    0.09
    å°±é¤IJ
    0.09
    è´£ç¼ĸ
    0.08
    çľ·
    0.08
    Activations Density 0.057%

    No Known Activations