© 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. 32938
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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
    åĵ¨
    -0.10
    åħį
    -0.09
     воÑĤ
    -0.09
    æľīæŶåĢĻ
    -0.09
    æ°´åŁŁ
    -0.09
    aran
    -0.09
    ç¾İçļĦ
    -0.08
    çķħéĶĢ
    -0.08
    çħ³
    -0.08
    ÙĪص
    -0.08
    POSITIVE LOGITS
     future
    0.10
    æľªæĿ¥
    0.10
    å¯¹æľªæĿ¥
    0.10
    æľªä¾Ĩ
    0.08
    grave
    0.08
     Future
    0.08
    èĬ¾
    0.08
     futuro
    0.08
    æľĢå¿«
    0.08
    éªĦåĤ²
    0.08
    Activations Density 0.038%

    No Known Activations