© 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. 35961
    Prev
    Next
    INDEX
    Explanations

    warming, cooling, fluids, wash

    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
    estre
    -0.09
    èľ¿
    -0.09
    éĩį伤
    -0.08
     bolt
    -0.08
    rell
    -0.08
    ql
    -0.08
    enet
    -0.08
    éķĮ
    -0.08
     componentName
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
    浸泡
    0.09
    俸
    0.09
    ativos
    0.09
    é«¡
    0.09
    rio
    0.09
    åĵĹ
    0.08
    agan
    0.08
    DMIN
    0.08
    .exchange
    0.08
    ctest
    0.08
    Activations Density 0.287%

    No Known Activations