© 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. 36223
    Prev
    Next
    INDEX
    Explanations

    writing about blogs

    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
     оÑĤд
    -0.09
    æĹĦ
    -0.09
    è¡·
    -0.08
    éĢģå¾Ģ
    -0.08
    олÑı
    -0.08
    ô
    -0.08
     Reception
    -0.08
    alted
    -0.08
    phies
    -0.08
    éĻ¬
    -0.08
    POSITIVE LOGITS
    é¼ĵ
    0.10
     blog
    0.10
    dit
    0.10
    blog
    0.09
    æĺ¨æĹ¥
    0.09
    ãĥĸãĥŃãĤ°
    0.09
     blogging
    0.08
    èĩªçĦ¶æĺ¯
    0.08
    Blog
    0.08
    åįļ客
    0.08
    Activations Density 0.392%

    No Known Activations