© 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. 48705
    Prev
    Next
    INDEX
    Explanations

    through to

    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
    èĮ«èĮ«
    -0.10
    aters
    -0.10
    åĩłçĤ¹
    -0.09
    ÅĽwiad
    -0.09
    ctors
    -0.09
    elib
    -0.09
    edelta
    -0.09
    éĤ£æł·çļĦ
    -0.09
    -serving
    -0.09
    å¸ĥæĭī
    -0.09
    POSITIVE LOGITS
     revis
    0.09
    ASET
    0.09
    bu
    0.08
    æĬĺåıł
    0.08
    çIJī
    0.08
    8
    0.07
     Guil
    0.07
    9
    0.07
    arella
    0.07
    aho
    0.07
    Activations Density 0.033%

    No Known Activations