© 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. 56395
    Prev
    Next
    INDEX
    Explanations

    lawyer legal law firms

    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
    çĶ¨èį¯
    -0.09
    æĬĽ
    -0.09
    éħįéĢģ
    -0.09
    å¼ķé¢Ĩ
    -0.08
    åİŁ
    -0.08
    ÄIJT
    -0.08
    esta
    -0.08
    æĭĽåķĨ
    -0.08
    ival
    -0.08
    æīĥ
    -0.08
    POSITIVE LOGITS
    æ³ķå¾ĭ
    0.14
    å¾ĭå¸Ī
    0.12
    å¾ĭ
    0.12
     ë²ķë¥ł
    0.12
     lawful
    0.12
    å¾ĭå¸ĪäºĭåĬ¡
    0.11
    æ³ķ令
    0.11
     lawy
    0.11
    æ³ķå¾ĭ顾éĹ®
    0.11
    legal
    0.11
    Activations Density 0.173%

    No Known Activations