© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    amusement rides

    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
     Rena
    -0.09
    æ»ŀ
    -0.09
    纳
    -0.09
    羡
    -0.09
    ç´į
    -0.09
    åį§å®¤
    -0.09
    åķĨæ¥Ń
    -0.08
    å¸Ľ
    -0.08
    éĽĨèģļ
    -0.08
    ifa
    -0.08
    POSITIVE LOGITS
     ride
    0.15
    ride
    0.13
    çļĦç»ıåİĨ
    0.13
     rides
    0.11
    rides
    0.11
     Ride
    0.11
    ä¸ĺ
    0.11
    åĽŀåij³
    0.11
     roller
    0.10
    æ»ĭåij³
    0.10
    Activations Density 0.075%

    No Known Activations