© 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. 4866
    Prev
    Next
    INDEX
    Explanations

    subject to revision

    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
    åĩĨ
    -0.09
    åĨ³
    -0.09
    å°ĨåĨĽ
    -0.09
    åħ¨åªĴä½ĵ
    -0.09
    ä¸Ģ对ä¸Ģ
    -0.08
    为ä¸ŃåĽ½
    -0.08
    5
    -0.08
    mph
    -0.08
     GIVEN
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    éĩįéĩį
    0.09
    丼
    0.09
     Westbrook
    0.09
    çķªèĮĦ
    0.09
    .lu
    0.09
    éĢıè§Ĩ
    0.09
    _dicts
    0.09
    空
    0.09
    ç°ª
    0.08
     Nil
    0.08
    Activations Density 0.023%

    No Known Activations