© 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. 11626
    Prev
    Next
    INDEX
    Explanations

    as per

    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
    åĵķ
    -0.10
    åģĥ
    -0.10
    èĩªé©¾
    -0.09
    ÙĨد
    -0.09
    æĸ¯åŁº
    -0.09
    _Offset
    -0.09
    åĽĽæĸ¹
    -0.08
    éī´åĪ«
    -0.08
    éĥ¨å§Ķ
    -0.08
    æ¦
    -0.08
    POSITIVE LOGITS
    ä¸ĢæŶ
    0.13
    çħ§æł·
    0.10
    affiliate
    0.09
    éķĢéĶĮ
    0.09
    obi
    0.08
    urtle
    0.08
    æľīä¸Ģä½į
    0.08
    -et
    0.08
    æ¼²
    0.08
    gué
    0.08
    Activations Density 0.158%

    No Known Activations