© 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. 27699
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

    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
     MDB
    -0.09
    ENTE
    -0.09
    罩
    -0.09
    toa
    -0.09
    StandardItem
    -0.09
    sey
    -0.09
    oux
    -0.08
    åĨĽåĽ¢
    -0.08
    agon
    -0.08
    hen
    -0.08
    POSITIVE LOGITS
     bufio
    0.11
    heets
    0.09
    æĴĩ
    0.09
    вÑıз
    0.09
    åħ¶æ¬¡
    0.09
    èĵIJ
    0.09
    èĢģ太太
    0.08
    ведениÑı
    0.08
    ìľĦ
    0.08
    aturday
    0.08
    Activations Density 0.237%

    No Known Activations