© 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. 11125
    Prev
    Next
    INDEX
    Explanations

    displayed, expression, demonstrated

    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
    åħ±åĪĽ
    -0.09
    ç¹ŀ
    -0.09
    lesh
    -0.09
    TestFixture
    -0.09
    _COMP
    -0.08
    æ±ĩæĢ»
    -0.08
    lund
    -0.08
     fortune
    -0.08
    åı¯æĥ³
    -0.08
    è¿Ļéĥ¨åĪĨ
    -0.08
    POSITIVE LOGITS
    å±ķçİ°åĩº
    0.16
    表çİ°
    0.16
    表çİ°åĩº
    0.16
    å±ķçİ°
    0.13
    å±ķçİ°äºĨ
    0.12
    表çݰ为
    0.12
    ä½ĵçİ°åĩº
    0.12
    æĺ¾
    0.12
    表çı¾
    0.11
    æĺ¾éľ²
    0.11
    Activations Density 0.124%

    No Known Activations