© 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. 27761
    Prev
    Next
    INDEX
    Explanations

    login to

    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
    ksam
    -0.10
    广大
    -0.09
    æĬ¼éĩij
    -0.08
    æĭľ
    -0.08
    大èĤ¡ä¸ľ
    -0.08
    å¹³æ°ij
    -0.08
    åľ¨è¿ĩ渡
    -0.08
    äºĽè®¸
    -0.08
    çŀ¥
    -0.08
    èħ°
    -0.08
    POSITIVE LOGITS
    åĬ²
    0.11
    าะ
    0.10
    ordo
    0.09
    ç»Ĵ
    0.09
     Ellison
    0.09
    CharArray
    0.09
    åİŁæĸĩåľ°åĿĢ
    0.09
    ndx
    0.09
    MES
    0.09
     Gaz
    0.08
    Activations Density 0.036%

    No Known Activations