© 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. 18230
    Prev
    Next
    INDEX
    Explanations

    field operations and locations

    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
    æİī
    -0.09
    åŃĺéĩı
    -0.09
    åĭĭ
    -0.09
    èµŀåĬ©
    -0.09
    elastic
    -0.09
    æĦıè¯Ĩ
    -0.09
     Lat
    -0.09
    ä¸įåıĹ
    -0.09
    宿
    -0.09
    åħ¨æĿij
    -0.09
    POSITIVE LOGITS
    çİ°åľº
    0.21
    çı¾åł´
    0.20
    å®ŀåľ°
    0.20
    åľ¨çİ°åľº
    0.18
    åīį线
    0.15
    æĸ½å·¥çİ°åľº
    0.15
    å®ŀéĻħæĥħåĨµ
    0.13
    éĩİå¤ĸ
    0.13
    åľ°éĿ¢
    0.13
    åĪ°åľº
    0.12
    Activations Density 0.086%

    No Known Activations