© 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. 60825
    Prev
    Next
    INDEX
    Explanations

    man LF

    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
    ãģ¾ãģĦ
    -0.09
    å±Ĭ
    -0.09
    éķ£
    -0.08
    åŁ´
    -0.08
    Unavailable
    -0.08
    åŃĹæł·
    -0.08
    ullet
    -0.08
     stake
    -0.08
    åĬłçĽĸ
    -0.08
     camel
    -0.08
    POSITIVE LOGITS
    åĽ¢éķ¿
    0.11
    åĽ¢
    0.11
    ç§ģæľį
    0.11
    åĽ¢åijĺ
    0.11
    åĽ¢è´Ń
    0.10
    éļ¾åº¦
    0.10
    uche
    0.09
    chs
    0.09
    еÑģÑĮ
    0.09
    PING
    0.09
    Activations Density 0.050%

    No Known Activations