© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8313
    Prev
    Next
    INDEX
    Explanations

    sprinklers, aberkip, hotel

    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
    ility
    -0.12
    биÑĤ
    -0.10
    بÙĪر
    -0.10
     каз
    -0.10
    /close
    -0.09
    Ñĩив
    -0.09
    igator
    -0.09
    ÑģÑĤвеннÑĭе
    -0.09
    enes
    -0.09
    åĿĢ
    -0.09
    POSITIVE LOGITS
    ../../../
    0.09
    éĺ¿å§¨
    0.08
    åѦç§ij
    0.08
    les
    0.08
    ners
    0.08
    åĥı个
    0.08
    åºĹéĩĮ
    0.08
    äºĨä¸Ģä¸ĭ
    0.08
    .Linked
    0.08
    £
    0.08
    Activations Density 0.002%

    No Known Activations