© 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. 39170
    Prev
    Next
    INDEX
    Explanations

    should be

    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
    ApplicationContext
    -0.08
    å°Ĩä¼ļ
    -0.08
    äºĨè¿ĩæĿ¥
    -0.08
    æĥŁ
    -0.08
    enk
    -0.08
    ä»ħ次äºİ
    -0.08
    æĭĶ
    -0.08
     waitFor
    -0.08
     Butterfly
    -0.08
    åĩłä¹İ
    -0.07
    POSITIVE LOGITS
    éģĩä¸Ĭ
    0.12
    åıijå±ķæ½ľåĬĽ
    0.10
    ä¸įæħİ
    0.10
    èĪ«
    0.10
    errar
    0.09
    åºĹ主
    0.09
    èĥ¸åīį
    0.09
    éĮ¯
    0.09
    éĶĻ
    0.09
    rup
    0.09
    Activations Density 0.014%

    No Known Activations