© 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. 5169
    Prev
    Next
    INDEX
    Explanations

    held back

    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
    åħ¨åĽ½äººæ°ij
    -0.10
    uet
    -0.10
    _FM
    -0.10
    æľĪæľ«
    -0.10
    æī¿æİ¥
    -0.10
    ëĿ½
    -0.10
    ä¸Ńåħ³
    -0.10
    åį°
    -0.09
    lei
    -0.09
    åijĬ
    -0.09
    POSITIVE LOGITS
    好äºĭ
    0.09
    olk
    0.08
    ä½ıäºĨ
    0.08
    ç»ıæµİæķĪçĽĬ
    0.08
    ered
    0.08
    缼åħ¸
    0.08
    _tid
    0.08
    ä½ı
    0.08
    ãģĽãģĦ
    0.07
     Pett
    0.07
    Activations Density 0.005%

    No Known Activations