© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    cannot find

    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
    /maps
    -0.10
    AMPL
    -0.09
    å¦Ĥæľīä¾µæĿĥ
    -0.09
    .proto
    -0.09
    CloseOperation
    -0.08
    é¦Ķ
    -0.08
    çľĭäºĨçľĭ
    -0.08
    åĪ»èĭ¦
    -0.08
    essaging
    -0.08
    ervers
    -0.08
    POSITIVE LOGITS
    å®īæİĴ
    0.09
    azz
    0.08
    ål
    0.08
    æĢİä¹ĪåĬŀ
    0.08
    åīįè¿°
    0.08
    ä¸Ĭè¿°
    0.08
     discre
    0.08
    éħĿéħ¿
    0.08
    æīİ
    0.07
    å¸ĥç½®
    0.07
    Activations Density 0.038%

    No Known Activations