© 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. 5576
    Prev
    Next
    INDEX
    Explanations

    future candidate skills

    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
    vang
    -0.10
    .vert
    -0.09
    erna
    -0.09
     Earn
    -0.09
    èģļä¼ļ
    -0.09
    elen
    -0.09
    äºĮèĢħ
    -0.09
    æĭ´
    -0.09
    è¾IJ
    -0.09
    éĻ·
    -0.08
    POSITIVE LOGITS
    åĢĻéĢī人
    0.11
    åĢĻéĢī
    0.11
    åºĶèģĺ
    0.10
     future
    0.09
    æ²Ĩ
    0.09
    Candidate
    0.09
    æľªæĿ¥
    0.09
     candidate
    0.09
    åľ¨æľªæĿ¥
    0.09
    å°ĨæĿ¥
    0.08
    Activations Density 0.038%

    No Known Activations