© 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. 58723
    Prev
    Next
    INDEX
    Explanations

    person performing action

    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
    estar
    -0.09
    ìĭ±
    -0.09
    (second
    -0.09
    оÑĩно
    -0.09
    èĥİ
    -0.09
     Associ
    -0.08
    å¤ĩ
    -0.08
    çºł
    -0.08
    quee
    -0.08
     rall
    -0.08
    POSITIVE LOGITS
    èĢħçļĦ
    0.15
    æĺ¯è°ģ
    0.12
    èĢħãģ®
    0.11
    说è¯Ŀ
    0.11
    åĤ¬çĶŁ
    0.10
    èĢħ
    0.10
    說話
    0.10
    å¼Ģåĩº
    0.10
    è¿Ļè¯Ŀ
    0.10
    åĪĽä½ľèĢħ
    0.10
    Activations Density 0.117%

    No Known Activations