© 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. 49265
    Prev
    Next
    INDEX
    Explanations

    colors and light

    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
    ä¸Ńåħ³æĿij
    -0.08
    çĸĸ
    -0.08
    缸æ¯Ķ
    -0.08
    对æłĩ
    -0.08
    çļĦä¸Ģ款
    -0.08
    asar
    -0.08
    æ²»
    -0.08
    æħİ
    -0.08
     Bold
    -0.08
    çĽ¸å¹²
    -0.07
    POSITIVE LOGITS
    èī²
    0.13
    é»Ħèī²
    0.12
    é¢ľèī²
    0.12
    绿èī²
    0.12
    çļĦé¢ľèī²
    0.12
    æ·¡
    0.10
     color
    0.10
    绿
    0.10
    ç¿ł
    0.10
    åħĪæĺ¯
    0.10
    Activations Density 0.119%

    No Known Activations