© 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. 21210
    Prev
    Next
    INDEX
    Explanations

    darkness and wilderness

    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
    å¾·å°Ķ
    -0.11
    æķ´å¤©
    -0.09
    çĪ·
    -0.09
    shop
    -0.09
    ä¸įéĶĻçļĦ
    -0.09
    sworth
    -0.09
    serter
    -0.09
    ãĢħ
    -0.08
    æľ¬ç½ij
    -0.08
    ç»
    -0.08
    POSITIVE LOGITS
    gli
    0.11
    lá
    0.11
    æ®Ĩ
    0.10
    oto
    0.10
    AndView
    0.09
    elf
    0.09
    åºŃéĻ¢
    0.09
    æĹĦ
    0.09
    åĭĥåĭĥ
    0.09
    ات
    0.09
    Activations Density 0.011%

    No Known Activations