© 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. 40159
    Prev
    Next
    INDEX
    Explanations

    stage platforms

    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
    SCO
    -0.10
     tide
    -0.09
    umo
    -0.09
    ookies
    -0.09
    ä¸Ńè¶ħ
    -0.09
    yal
    -0.09
    ookie
    -0.09
    pei
    -0.08
    åIJ¬è¯´
    -0.08
    alus
    -0.08
    POSITIVE LOGITS
    åı°ä¸Ĭ
    0.14
    åı°
    0.14
    èĩº
    0.12
    èĪŀåı°
    0.10
    éĶ£
    0.10
    æĺ¯åĽ½åĨħ
    0.10
    åĩłæŃ¥
    0.10
    åĺī宾
    0.10
    éĺ¶
    0.09
    åīįåı°
    0.09
    Activations Density 0.055%

    No Known Activations