© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21393
    Prev
    Next
    INDEX
    Explanations

    pinch of salt

    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
    绩
    -0.10
    è°ł
    -0.09
    epar
    -0.09
    untime
    -0.09
     torment
    -0.09
     обÑĥÑĩ
    -0.09
    rup
    -0.09
    mun
    -0.08
    mue
    -0.08
     Bans
    -0.08
    POSITIVE LOGITS
     dose
    0.15
    åīĤéĩı
    0.15
     doses
    0.12
    isme
    0.10
    ä¸ĢçĤ¹
    0.10
    满满çļĦ
    0.10
    è¿Ļ份
    0.09
    æľīä¸ĢçĤ¹
    0.09
    æĢĢçĸij
    0.09
    注åħ¥
    0.09
    Activations Density 0.074%

    No Known Activations