© 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. 6440
    Prev
    Next
    INDEX
    Explanations

    by followed by articles

    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
    axes
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.08
    inals
    -0.08
    Ùħات
    -0.08
    åŁºæľ¬åİŁåĪĻ
    -0.08
     Ragnar
    -0.08
     ÑĥÑĩеб
    -0.08
    ToList
    -0.07
    ÙĬات
    -0.07
    èµ·æĿ¥
    -0.07
    POSITIVE LOGITS
    éĤ£ä»½
    0.10
    çľ¼åīįçļĦ
    0.10
    éĤ£åıª
    0.09
    èºĶ
    0.09
     how
    0.09
    éĤ£äºĽ
    0.09
    éĤ£æ®µ
    0.09
    ãĤ«ãĥ³
    0.09
    å®Ľ
    0.09
    .hw
    0.09
    Activations Density 0.028%

    No Known Activations