© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10469
    Prev
    Next
    INDEX
    Explanations

    url prefixes and delimiters

    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
    oha
    -0.08
     ngá»Ļ
    -0.08
    审
    -0.08
     ROLE
    -0.08
    /edit
    -0.08
    lymp
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    /pop
    -0.07
    acom
    -0.07
    æĻļæľŁ
    -0.07
    POSITIVE LOGITS
    çIJħ
    0.10
    çıł
    0.09
    糨
    0.09
    è§ĦèĮĥ
    0.09
    æľ¬çĿĢ
    0.09
    .fm
    0.09
    åįĥéĩĮ
    0.09
    太平æ´ĭ
    0.09
    ursive
    0.08
    å®ŀ践活åĬ¨
    0.08
    Activations Density 0.041%

    No Known Activations