© 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. 63201
    Prev
    Next
    INDEX
    Explanations

    exclamation marks

    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
    isable
    -0.09
    ick
    -0.09
    izr
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    ccess
    -0.08
     mgr
    -0.08
    æľ´
    -0.08
    æŁIJç§į
    -0.08
    æ°ijæĹı
    -0.07
    绵
    -0.07
    POSITIVE LOGITS
    yer
    0.09
    HING
    0.09
    sWith
    0.09
     ìķĦëĭĮ
    0.09
    人çĶŁçļĦ
    0.09
    èµ£
    0.09
    âĬ£
    0.08
    omat
    0.08
    tres
    0.08
    zos
    0.08
    Activations Density 0.061%

    No Known Activations