© 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. 5110
    Prev
    Next
    INDEX
    Explanations

    every time i

    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
    erus
    -0.10
    icy
    -0.10
    åĭĭ
    -0.09
    olem
    -0.08
    èĩ¾
    -0.08
     оÑĤд
    -0.08
    åıĺæĪIJäºĨ
    -0.08
    ptic
    -0.08
    äºĨèµ·æĿ¥
    -0.08
    ibase
    -0.08
    POSITIVE LOGITS
    çļĦåį°è±¡
    0.09
    éĥ½è§īå¾Ĺ
    0.09
    è¾ĸ
    0.09
    æĪĺå½¹
    0.09
    ä¼´
    0.09
     preceding
    0.08
    人æ°Ķ
    0.08
    HW
    0.08
    æĪijå¿ĥéĩĮ
    0.08
    年人
    0.08
    Activations Density 0.014%

    No Known Activations