© 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. 63137
    Prev
    Next
    INDEX
    Explanations

    -centered, -oriented, about you

    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
     overs
    -0.09
    çģµæĦŁ
    -0.08
     ev
    -0.08
     rig
    -0.08
     permanent
    -0.08
    Official
    -0.07
    太平
    -0.07
    大èĩ£
    -0.07
    å®ĺæĸ¹
    -0.07
     official
    -0.07
    POSITIVE LOGITS
    为ä¸Ńå¿ĥ
    0.15
    ä¸Ńå¿ĥ
    0.13
    ä½ľèĢħæľ¬äºº
    0.13
     ì¤ijìĭ¬
    0.12
    åĽ´çĿĢ
    0.11
    å¾Ģå¤ĸ
    0.10
    ä¸Ńå¿ĥ主任
    0.10
    -centric
    0.10
    æķĽ
    0.10
    -centered
    0.10
    Activations Density 0.052%

    No Known Activations