© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52701
    Prev
    Next
    INDEX
    Explanations

    petrol engine variants

    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
    adol
    -0.10
    vit
    -0.10
    anter
    -0.09
     contato
    -0.09
    ä¸ļæĢģ
    -0.09
     vit
    -0.08
    éĵ¾
    -0.08
     Finger
    -0.08
    åijĺ
    -0.08
    illis
    -0.08
    POSITIVE LOGITS
    creativecommons
    0.09
    utors
    0.09
    -powered
    0.09
    inka
    0.09
    powered
    0.08
    åıijåĬ¨æľº
    0.08
    åĬ¨åĬĽ
    0.08
    æĮ½åĽŀ
    0.08
    .pub
    0.08
    桦
    0.08
    Activations Density 0.017%

    No Known Activations