© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    test or testimonial

    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
    ARC
    -0.10
    åĨįéĢł
    -0.10
    thon
    -0.10
     ARC
    -0.09
    èī°è¾Ľ
    -0.09
    弧
    -0.09
    cul
    -0.09
     íĺ¸
    -0.09
    å¹²åĺĽ
    -0.09
    urma
    -0.09
    POSITIVE LOGITS
    imonials
    0.17
    imonial
    0.15
    osterone
    0.13
    [Test
    0.12
    /test
    0.12
     TEST
    0.11
    imony
    0.11
    (TEST
    0.11
    =test
    0.11
    (test
    0.11
    Activations Density 0.162%

    No Known Activations