© 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. 56402
    Prev
    Next
    INDEX
    Explanations

    organizational units

    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
     grac
    -0.08
    elter
    -0.08
    embro
    -0.08
    اش
    -0.08
    涮
    -0.08
    elog
    -0.08
    lich
    -0.08
    opper
    -0.08
    yna
    -0.08
    AtA
    -0.08
    POSITIVE LOGITS
    phan
    0.11
     thereof
    0.10
    åŀĤ
    0.09
     kê
    0.09
    人æīį
    0.09
    .Exists
    0.09
    å·²ç»ıåľ¨
    0.09
    èĩªè´Ł
    0.09
    寻
    0.09
    antee
    0.08
    Activations Density 0.047%

    No Known Activations