© 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. 38993
    Prev
    Next
    INDEX
    Explanations

    convention center 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
    opa
    -0.12
    çıŃéķ¿
    -0.11
    ntl
    -0.11
    ktop
    -0.11
    ç»ıèIJ¥æ´»åĬ¨
    -0.10
    æľªæĿ¥åıijå±ķ
    -0.10
    ä¹ĭ乡
    -0.10
    éħµ
    -0.10
    大å¹ħ
    -0.10
    å¹´æĿ¥
    -0.10
    POSITIVE LOGITS
    9
    0.10
    1
    0.10
    3
    0.10
    0
    0.09
    4
    0.09
    5
    0.09
    å±ķé¦Ĩ
    0.09
    7
    0.09
    8
    0.09
    6
    0.08
    Activations Density 0.052%

    No Known Activations