© 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. 58379
    Prev
    Next
    INDEX
    Explanations

    bee, hive, and apiculture

    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
    åĿļå®ļä¸į
    -0.10
     mar
    -0.09
    鹿
    -0.08
    åı¯éĿłæĢ§
    -0.08
    pike
    -0.08
    èij³
    -0.08
    _crypto
    -0.08
    gtest
    -0.08
    éĢģæĿ¥
    -0.08
    æŀ¯çĩ¥
    -0.08
    POSITIVE LOGITS
    èľľèľĤ
    0.12
    èľĤ
    0.11
    大èĥĨ
    0.11
    èľĤèľľ
    0.11
    æłĸ
    0.10
    èľľ
    0.10
    èľĩ
    0.10
    åħ»
    0.10
     honey
    0.10
    bee
    0.09
    Activations Density 0.047%

    No Known Activations