© 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. 22497
    Prev
    Next
    INDEX
    Explanations

    before followed by a noun or gerund

    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
     Esk
    -0.10
    urdy
    -0.09
    åĪ°è¿ĻéĩĮ
    -0.09
    ilik
    -0.09
    为ä½ķ
    -0.08
    æķĻè®Ń
    -0.08
    åĽ´çĿĢ
    -0.08
    å°ijåIJĥ
    -0.08
    parity
    -0.08
    ylan
    -0.08
    POSITIVE LOGITS
    ä¸ĢèĦļ
    0.12
    åį³å°ĨåĪ°æĿ¥
    0.09
    .setter
    0.09
     garn
    0.09
    å°ļ
    0.09
    AFX
    0.09
    æĭĺ
    0.08
    ç¦ıå¾·
    0.08
    æ¯ı次éĥ½
    0.08
    沦
    0.08
    Activations Density 0.045%

    No Known Activations