© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 54546
    Prev
    Next
    INDEX
    Explanations

    questions starting with "how" or "is the"

    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
    aper
    -0.08
    ç·
    -0.08
    èĭ«
    -0.08
    éĿ³
    -0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    座ä½į
    -0.08
    EPS
    -0.08
    aman
    -0.08
    icularly
    -0.07
    èĵĿ天
    -0.07
    POSITIVE LOGITS
    ÂŃi
    0.09
    ÂŃing
    0.08
    .WaitFor
    0.08
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    ç½¹
    0.08
    ÂŃs
    0.08
    çĴĥ
    0.08
     Parsons
    0.07
    .Listener
    0.07
    İÅŀ
    0.07
    Activations Density 2.780%

    No Known Activations