© 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. 29469
    Prev
    Next
    INDEX
    Explanations

    right or left side

    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
    åĪ°å¤Ħ
    -0.09
     bom
    -0.09
    çªģ
    -0.08
    summer
    -0.08
    ç©´
    -0.08
    erm
    -0.08
    æŀķ
    -0.08
    åħ¨åijĺ
    -0.08
    rys
    -0.08
    deg
    -0.08
    POSITIVE LOGITS
     ниже
    0.14
     below
    0.13
    below
    0.13
    åı³æīĭ
    0.11
    åı³
    0.11
    ä¸ĭéĿ¢
    0.10
    åı³ä¾§
    0.09
     abaixo
    0.09
    åĪĹåĩº
    0.09
    GEST
    0.09
    Activations Density 0.027%

    No Known Activations