© 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. 23855
    Prev
    Next
    INDEX
    Explanations

    offer / quote / proposal

    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
    gere
    -0.09
    earch
    -0.09
    mma
    -0.09
    /ph
    -0.09
    ardi
    -0.08
    åĢ¨
    -0.08
    äºı
    -0.08
    交ä¼ļ
    -0.08
    edian
    -0.08
    uning
    -0.08
    POSITIVE LOGITS
    iginal
    0.11
    à¹ģà¸Ļะ
    0.11
    ãģĹãģı
    0.10
    丰满
    0.10
    lags
    0.10
    acle
    0.09
     Äijá»ı
    0.09
    ળ
    0.09
    REEN
    0.09
    GRES
    0.09
    Activations Density 0.012%

    No Known Activations