© 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. 22849
    Prev
    Next
    INDEX
    Explanations

    watching or witnessing

    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
    ä½ľåĩºäºĨ
    -0.09
    ZO
    -0.09
    éĽĨæĪIJ
    -0.09
    好åIJĹ
    -0.09
    çĻ£
    -0.09
    å°ijæķ°
    -0.08
     Points
    -0.08
    ä¸Ģè¡Į
    -0.08
    å°ijéĩı
    -0.08
    æ¤įåħ¥
    -0.08
    POSITIVE LOGITS
    çľĭçĿĢ
    0.18
    çľĭåĪ°
    0.17
    缮çĿ¹
    0.16
    åľ°çľĭçĿĢ
    0.16
     witnessing
    0.15
    è§Ĥçľĭ
    0.15
    çľĭèijĹ
    0.15
     watching
    0.15
    çľĭè§ģ
    0.14
    åIJ¬è§ģ
    0.13
    Activations Density 0.117%

    No Known Activations