© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21886
    Prev
    Next
    INDEX
    Explanations

    search for, job after, or tenure for

    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
    麻çĹ¹
    -0.10
    ullo
    -0.09
    abler
    -0.09
     tá
    -0.08
    ä½ľä¸ļ
    -0.08
     Moj
    -0.08
    é»Ħéĩij
    -0.08
    çİĭåŃIJ
    -0.08
    CursorPosition
    -0.08
     Tok
    -0.08
    POSITIVE LOGITS
    è¿°èģĮ
    0.11
    èģĺ
    0.11
    åħ¬å¼ĢæĭĽèģĺ
    0.11
    å¤ĩ
    0.10
    ä½ĵæ£Ģ
    0.10
    åºĶèģĺ
    0.10
    åĪĽéĢłæĢ§
    0.09
    æĭĽèģĺ
    0.09
    èģĮ称
    0.09
    æ±Ģ
    0.09
    Activations Density 0.054%

    No Known Activations