© 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. 5625
    Prev
    Next
    INDEX
    Explanations

    diversity or diverse contexts

    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
    ister
    -0.10
    rollers
    -0.09
    zeug
    -0.09
    /or
    -0.09
     Bowling
    -0.08
    sp
    -0.08
    ains
    -0.08
    ters
    -0.08
    endez
    -0.08
    achi
    -0.08
    POSITIVE LOGITS
    -minded
    0.11
    ë¡Ń
    0.10
    iates
    0.10
    ç½ijå°ıç¼ĸ
    0.10
    åĩºå±Ģ
    0.09
    ÙĬØ«
    0.09
    æĻļæĬ¥
    0.09
    ität
    0.09
    çĶµç«Ļ
    0.09
    iat
    0.09
    Activations Density 0.021%

    No Known Activations