© 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. 35982
    Prev
    Next
    INDEX
    Explanations

    English and foreign character sequences

    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
    åIJĦå¼ıåIJĦæł·
    -0.10
    没æľīæĥ³åĪ°
    -0.09
    å¦ĵ
    -0.09
    Street
    -0.09
    å¨ij
    -0.09
    åħ³äºİæĪij们
    -0.09
    USTER
    -0.09
    éĥ½æĺ¯éĿŀ常
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    apist
    -0.09
    POSITIVE LOGITS
    mys
    0.11
    igs
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    åĵªç§į
    0.09
    éĢļ常æĺ¯
    0.08
    èIJį
    0.08
    uds
    0.08
    igy
    0.08
     piv
    0.08
    åīįèĢħ
    0.07
    Activations Density 0.106%

    No Known Activations