© 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. 29961
    Prev
    Next
    INDEX
    Explanations

    heaven and heavenly phrases

    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
    ivity
    -0.10
    TURE
    -0.10
    ðŁı»
    -0.10
    ä½ĵåĨħ
    -0.09
    平淡
    -0.09
    sing
    -0.09
    иÑĢовка
    -0.09
    ingly
    -0.09
    ément
    -0.09
    ulary
    -0.09
    POSITIVE LOGITS
    /or
    0.11
    lining
    0.11
    reich
    0.10
    izer
    0.10
    tri
    0.10
    AGO
    0.09
    ened
    0.09
    ç¼Ń
    0.09
    (TM
    0.09
    à¹Ģหล
    0.09
    Activations Density 0.006%

    No Known Activations