© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    water and related environments

    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
    èĢĢ
    -0.08
    CI
    -0.08
    踮
    -0.08
    åįłæľī
    -0.08
    ä¸Ńä¿Ħ
    -0.08
    éĢĴç»Ļ
    -0.08
    èĻĶ
    -0.08
    æ¶Ĥ
    -0.08
    ressing
    -0.08
     extern
    -0.08
    POSITIVE LOGITS
    æ°´éĩı
    0.11
    çĸĨ
    0.10
    èĬ±èįī
    0.10
    èħIJ
    0.10
    æ°´è´¨
    0.09
    .Fatalf
    0.09
     далÑĮÑĪе
    0.09
    ILLE
    0.09
    èĩŃ
    0.09
     HDF
    0.09
    Activations Density 0.073%

    No Known Activations