© 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. 49479
    Prev
    Next
    INDEX
    Explanations

    building momentum

    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
    å¾Īæ·±
    -0.08
    人åĿĩ
    -0.08
    æĽ´æ·±
    -0.08
    å½¹
    -0.08
    åIJĪä½ľåįıè®®
    -0.08
    ä¸įå·²
    -0.08
    çĥŁåĽ±
    -0.08
    对å¤ĸ
    -0.08
    æľĪä¸Ń
    -0.08
    Inputs
    -0.08
    POSITIVE LOGITS
    åĬ¿å¤´
    0.14
     momentum
    0.13
    åĬĽåº¦
    0.11
    åĬ¿
    0.11
    åĬ¨èĥ½
    0.10
    çĥŃ度
    0.10
     traction
    0.10
    omentum
    0.10
    è¼ī
    0.10
     Shades
    0.10
    Activations Density 0.055%

    No Known Activations