© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    firsthand experience or direct observation

    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
    [out
    -0.08
    mith
    -0.08
    uard
    -0.08
    osphere
    -0.08
    ä¸ĭ乡
    -0.08
    ested
    -0.08
    åħ±åIJĮä½ĵ
    -0.08
    uer
    -0.08
    asco
    -0.08
    éĴĪ对æĢ§
    -0.08
    POSITIVE LOGITS
    缮çĿ¹
    0.12
    亲身
    0.11
    çĿ¹
    0.10
    /front
    0.10
    æĦŁåıĹåĪ°äºĨ
    0.10
    LEE
    0.09
    èĻı
    0.09
    .opensource
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    æĦŁåıĹåĪ°
    0.09
    Activations Density 0.005%

    No Known Activations