© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52136
    Prev
    Next
    INDEX
    Explanations

    glacier delineation

    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
    å¸Ń
    -0.10
    éĿ©
    -0.09
    iban
    -0.09
    éģIJ
    -0.09
    .stride
    -0.09
    èĪĴéĢĤçļĦ
    -0.09
    CRET
    -0.09
     mesh
    -0.09
    æłı
    -0.09
    LETE
    -0.08
    POSITIVE LOGITS
    人åĬĽ
    0.10
    循
    0.09
     glacier
    0.09
     /\.
    0.09
    æ´»æĢ§
    0.09
    çŃı
    0.09
    çijŀ士
    0.09
     bumper
    0.08
    æīĭåĬ¨
    0.08
    åºĬ
    0.08
    Activations Density 0.055%

    No Known Activations