© 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. 38660
    Prev
    Next
    INDEX
    Explanations

    capacity of storage or network

    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
    ness
    -0.11
    inary
    -0.09
    ãģıãĤĭ
    -0.09
    -fashioned
    -0.09
    çĥ¯
    -0.09
    оÑģÑĮ
    -0.08
    zeug
    -0.08
    à¸IJาà¸Ļ
    -0.08
    \Lib
    -0.08
    iness
    -0.08
    POSITIVE LOGITS
    -bodied
    0.12
    è¿ĩåī©
    0.10
    olla
    0.09
    dam
    0.09
    nel
    0.09
    arian
    0.09
    sed
    0.09
    ional
    0.09
    ionate
    0.09
    åŀ¢
    0.09
    Activations Density 0.036%

    No Known Activations