© 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. 54173
    Prev
    Next
    INDEX
    Explanations

    social media and networks

    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
    orth
    -0.10
    ì¹ĺ
    -0.09
    ubb
    -0.09
    unsch
    -0.08
    æ¤Ł
    -0.08
    elin
    -0.08
    æ¸ļ
    -0.08
    潺
    -0.08
    缴éĢļ车
    -0.08
    åģ»
    -0.08
    POSITIVE LOGITS
    åij¼
    0.10
    çĨ¹
    0.09
    åIJĿ
    0.09
    è¾į
    0.08
    åĮĸçļĦ
    0.08
    ni
    0.08
    åѦåĪ°
    0.08
    etus
    0.08
    /twitter
    0.08
    åĮĸ
    0.08
    Activations Density 0.012%

    No Known Activations