© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35764
    Prev
    Next
    INDEX
    Explanations

    not enough

    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
    éĤ
    -0.09
    èĩ³å°ij
    -0.09
     reasonably
    -0.09
     bere
    -0.08
    认åı¯
    -0.08
    telegram
    -0.08
    çĥŁèĬ±
    -0.08
    æīĭ游
    -0.08
    åIJĪçIJĨ
    -0.08
    ìŀĺ
    -0.08
    POSITIVE LOGITS
    çĥĪ
    0.11
    åħį
    0.11
    å«¡
    0.10
    ä¸ī代
    0.09
    éĤ£ç§į
    0.09
    åħ¨é¢Ŀ
    0.09
    æĭĺ
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    åħ¨æ°ij
    0.09
    åħ¨èĩªåĬ¨
    0.09
    Activations Density 0.048%

    No Known Activations