© 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. 39916
    Prev
    Next
    INDEX
    Explanations

    insertion of objects

    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
    สà¸Ķ
    -0.10
    人人
    -0.09
    éĶ·
    -0.09
    ENA
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    bers
    -0.09
    ãģĿ
    -0.08
    åĸĿèĮ¶
    -0.08
     Ñģвоим
    -0.08
    èĩªå·±
    -0.08
    POSITIVE LOGITS
    opensource
    0.11
    éļ¾
    0.10
    çĢij
    0.09
    æĪİ
    0.09
    æ²¾
    0.09
    allas
    0.09
    注æĺİåĩºå¤Ħ
    0.09
    åıĺ为
    0.08
    æĺĻ
    0.08
    åĬ¨èĥ½
    0.08
    Activations Density 0.003%

    No Known Activations