© 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. 34109
    Prev
    Next
    INDEX
    Explanations

    baby and infant contexts

    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
    åĭĭ
    -0.08
     تÙĤدÙĬ
    -0.08
    eshire
    -0.08
    å®ļæŶ
    -0.08
     Marion
    -0.08
    .Drawable
    -0.08
    åĨ°ç®±
    -0.08
    æĪijçĪ±ä½ł
    -0.08
    ä½İä¿Ŀ
    -0.08
    对åѦçĶŁ
    -0.08
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.10
    å¿ħéľĢ
    0.10
    æ¶Ķ
    0.09
    éĢļåħ³
    0.09
    æ¿ł
    0.09
    ÑĢÑĥж
    0.09
    éĢļè¡Į
    0.09
    çĻ»éĻĨ
    0.08
    åĿĬ
    0.08
    åľºä¸Ĭ
    0.08
    Activations Density 0.014%

    No Known Activations