© 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. 5871
    Prev
    Next
    INDEX
    Explanations

    corporate governance and leadership roles

    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
    ç¥
    -0.10
    å®ĺ
    -0.10
     Dial
    -0.09
    ä¸Ģæĸ¹
    -0.09
    äºī龸
    -0.08
    åĸ·æ¶Ĥ
    -0.08
    usk
    -0.08
    PTS
    -0.08
    lico
    -0.08
    åİŁæłĩé¢ĺ
    -0.08
    POSITIVE LOGITS
    é£İéĻ©ç®¡çIJĨ
    0.10
    çļĦé£İéĻ©
    0.10
    éĺ²èĮĥ
    0.10
    æĹłç¼Ŀ
    0.10
    é£İæݧ
    0.09
    risk
    0.09
    æīģ
    0.09
    éĢIJ
    0.09
    æ¼Ķ
    0.09
    éĤ¸
    0.09
    Activations Density 0.064%

    No Known Activations