© 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. 28129
    Prev
    Next
    INDEX
    Explanations

    recycle, recycled, recycling

    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
    alog
    -0.11
    IMP
    -0.10
    est
    -0.10
    cut
    -0.09
    lique
    -0.09
    /questions
    -0.09
    azes
    -0.09
     Zot
    -0.09
    resses
    -0.09
    orney
    -0.09
    POSITIVE LOGITS
    /rec
    0.08
    äºĨè¿ĩæĿ¥
    0.08
    ção
    0.08
     tá»ij
    0.08
    inq
    0.08
    åĩºå±Ģ
    0.08
    åİ¢
    0.08
    äºĨä¸Ģä¸ĭ
    0.08
    -friendly
    0.08
    /general
    0.08
    Activations Density 0.019%

    No Known Activations