© 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. 27195
    Prev
    Next
    INDEX
    Explanations

    Argo, ARGUS, Records, Aframe

    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
    éĵĨ
    -0.12
    éĢıè§Ĩ
    -0.10
    尽头
    -0.10
    æ¼ł
    -0.10
    æİĢ
    -0.10
    æ½Ń
    -0.10
    éĴı
    -0.10
    ä¼ļè§īå¾Ĺ
    -0.10
    åħ¬å¼Ģåıij
    -0.10
    åŃij
    -0.09
    POSITIVE LOGITS
    è¸ı
    0.09
    ioc
    0.09
    身份
    0.08
    omaly
    0.08
    ETA
    0.08
     underst
    0.08
    chooser
    0.08
     infl
    0.07
    roy
    0.07
     identity
    0.07
    Activations Density 0.001%

    No Known Activations