© 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. 27344
    Prev
    Next
    INDEX
    Explanations

    combinations and installations

    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
    æįĤ
    -0.10
    åĬłå·¥åİĤ
    -0.09
    åĩ¿
    -0.08
    ä½ľåĵģåĨħ容
    -0.08
    _PD
    -0.08
    éĩįè¿Ķ
    -0.08
    amac
    -0.08
    _algo
    -0.08
    è¿ĩåħ³
    -0.08
    .GetAsync
    -0.08
    POSITIVE LOGITS
    éħįç½®
    0.10
    管çIJĨåijĺ
    0.10
    ढ
    0.09
    éĽĦ
    0.09
     bullet
    0.08
     farm
    0.08
    å®Ĺ
    0.08
    евиÑĩ
    0.08
    è¡°
    0.08
     port
    0.08
    Activations Density 0.714%

    No Known Activations