© 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. 52911
    Prev
    Next
    INDEX
    Explanations

    lemonade, lime, street, cay, duct

    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
    imming
    -0.09
    ording
    -0.09
    à¸Ħà¸Ńย
    -0.09
    erval
    -0.09
    aniem
    -0.09
    é¥
    -0.09
    uing
    -0.09
    urally
    -0.09
    âĵ
    -0.09
    ëĦĺ
    -0.09
    POSITIVE LOGITS
    nier
    0.14
    ettes
    0.12
    ette
    0.10
    ality
    0.10
    éĻĽ
    0.10
    æĻ°
    0.10
    Ñİ
    0.10
    iable
    0.10
    æ±ģ
    0.09
    cellent
    0.09
    Activations Density 0.004%

    No Known Activations