© 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. 32476
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    åıĮåıĮ
    -0.08
    æĪ¶
    -0.08
    ÑģÑĤÑĮ
    -0.08
    etten
    -0.08
    æİł
    -0.08
    è§ĤæľĽ
    -0.08
    irim
    -0.08
    æĭĬ
    -0.08
    åı¯ä»¥çĽ´æİ¥
    -0.08
    ä¹ŁæĹłæ³ķ
    -0.08
    POSITIVE LOGITS
    ilies
    0.11
    ä¸Ģ段
    0.11
    unas
    0.10
    æŬ
    0.09
    à¤
    0.09
    osti
    0.09
    帮ä»ĸ
    0.08
    å¯Įæľī
    0.08
    iten
    0.08
    ites
    0.08
    Activations Density 0.001%

    No Known Activations