© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59421
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    Negative Logits
    AINS
    -0.09
    legg
    -0.09
    èĻŀ
    -0.09
     incom
    -0.09
    ãģ¯ãģļãģ§ãģĻ
    -0.09
    ãģ©ãģĵãĤį
    -0.09
    大å®Ĺ
    -0.09
    leur
    -0.09
    hec
    -0.09
    ÅĽl
    -0.08
    POSITIVE LOGITS
    6
    0.10
     Pron
    0.10
    éĥ½ä¸įèĥ½
    0.10
    5
    0.09
    9
    0.09
    2
    0.09
    åı¯ä»¥è¯´æĺ¯
    0.09
    شد
    0.09
    4
    0.09
    å·¦åı³
    0.09
    Activations Density 0.151%

    No Known Activations