© 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. 34274
    Prev
    Next
    INDEX
    Explanations

    "in" followed by various words

    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
    è¿Ļ次
    -0.09
    ÑĢог
    -0.08
    åģĥ
    -0.08
    HASH
    -0.08
    åѱ
    -0.08
    å´ĸ
    -0.08
    夺
    -0.08
    лÑĥÑĪ
    -0.08
    çľī
    -0.08
    åĽ½æĥħ
    -0.08
    POSITIVE LOGITS
    ema
    0.10
    俳
    0.10
    èĤ
    0.09
    ç°ı
    0.09
    æĬĬè¿Ļ个
    0.09
    å¹£
    0.08
    éĵ¢
    0.08
    �t
    0.08
    fas
    0.08
    .joda
    0.08
    Activations Density 0.247%

    No Known Activations