© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 56934
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    念
    -0.09
    çķ¥
    -0.09
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.08
    èĽ®
    -0.08
    顯示
    -0.08
    _suffix
    -0.08
    è¡ĮæĶ¿éĥ¨éŨ
    -0.08
    åĿļ
    -0.08
    äºĭåIJİ
    -0.08
    å®Įåħ¨
    -0.08
    POSITIVE LOGITS
    以åıĬ
    0.19
    以åıĬåħ¶ä»ĸ
    0.17
     serta
    0.15
     sowie
    0.13
     oraz
    0.12
    æŃ¤å¤ĸ
    0.12
     باÙĦإضاÙ쨩
    0.11
     ÑĤакже
    0.11
    itionally
    0.10
    çĿĢä»ĸ
    0.10
    Activations Density 0.094%

    No Known Activations