© 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. 48712
    Prev
    Next
    INDEX
    Explanations

    Lamb waves, streamers, contact, waves

    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
    ä½£
    -0.09
    ละ
    -0.09
    ายà¸Ļ
    -0.09
    æĺ´
    -0.08
    款项
    -0.08
     prelim
    -0.08
    åŁ¹
    -0.08
    æĺĻ
    -0.08
    èĥĮéĥ¨
    -0.08
     edi
    -0.08
    POSITIVE LOGITS
    ringe
    0.11
    声
    0.11
    èģ²
    0.11
    ä½İ声
    0.11
    æĭ¾
    0.10
    (sound
    0.10
    æĺķ
    0.09
    otr
    0.09
    éŁ¿
    0.09
    åIJ¬è§ģ
    0.09
    Activations Density 0.152%

    No Known Activations