© 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. 23775
    Prev
    Next
    INDEX
    Explanations

    use to practice law

    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
    ums
    -0.10
     ÑĢеж
    -0.10
     ÑĥÑģп
    -0.09
     bully
    -0.09
    SCII
    -0.09
    irut
    -0.09
    .buf
    -0.09
    WebKit
    -0.09
    ispens
    -0.09
    uite
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.11
    è¿Ļ个æĹ¶ä»£
    0.11
     данного
    0.10
    æѤ类
    0.09
    èĩªè´¸
    0.09
    è¿Ļä¹Ī大
    0.09
     даннÑĭй
    0.09
    è¿Ļæł·åģļ
    0.09
    åĹĵ
    0.09
    æŃ¤é¡¹
    0.09
    Activations Density 0.087%

    No Known Activations