© 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. 55594
    Prev
    Next
    INDEX
    Explanations

    cookie or cookies

    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
    à¹Ĥ
    -0.11
    å¥
    -0.10
    .shtml
    -0.09
    soc
    -0.09
    arness
    -0.09
    æīĩ
    -0.09
    ovah
    -0.09
    $_['
    -0.09
    æ¹Ł
    -0.09
     TOD
    -0.09
    POSITIVE LOGITS
    cookies
    0.13
     cookies
    0.13
     cookie
    0.10
    çģ°å°ĺ
    0.09
    åİī
    0.09
     Cookies
    0.09
    cookie
    0.09
    Cookies
    0.09
    颧
    0.09
    æĶ¶éĽĨ
    0.09
    Activations Density 0.116%

    No Known Activations