© 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. 53626
    Prev
    Next
    INDEX
    Explanations

    rumors and related words

    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
    ives
    -0.09
    mium
    -0.09
    emme
    -0.09
    aan
    -0.09
    à¹Į
    -0.09
    æľīæľºä¼ļ
    -0.08
    inch
    -0.08
    åı¯æĥ³
    -0.08
    çī¢åĽº
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    POSITIVE LOGITS
    ulator
    0.10
    ç»Ŀ
    0.09
    ULATOR
    0.09
    å·²ä¹ħçļĦ
    0.09
    aging
    0.09
    azon
    0.09
    ned
    0.09
    ulates
    0.08
    sealed
    0.08
    cle
    0.08
    Activations Density 0.009%

    No Known Activations