© 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. 56820
    Prev
    Next
    INDEX
    Explanations

    crush and created

    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
    ally
    -0.15
    ALLY
    -0.10
    /legal
    -0.10
    س
    -0.10
    åijĺ
    -0.09
    ities
    -0.09
    ality
    -0.09
    reck
    -0.09
    SON
    -0.09
    etro
    -0.09
    POSITIVE LOGITS
    ingly
    0.19
    åľ°ä¸Ńæµ·
    0.10
    çł
    0.10
    edList
    0.10
    ably
    0.10
    æĥħ人
    0.10
    sed
    0.10
    à¸Ĺาà¸ĩ
    0.10
    nap
    0.09
    çĶµç«Ļ
    0.09
    Activations Density 0.005%

    No Known Activations