© 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. 61166
    Prev
    Next
    INDEX
    Explanations

    sky-high

    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
    èĭ±éĽĦ
    -0.10
    çĭ¬ç«ĭ
    -0.09
    ogi
    -0.09
    ferences
    -0.09
     иÑģкÑĥÑģÑģÑĤв
    -0.08
    å½¢çĬ¶
    -0.08
    çļĦ形象
    -0.08
    uers
    -0.08
    ATER
    -0.08
     prer
    -0.08
    POSITIVE LOGITS
    å±ĭ顶
    0.10
    ãĤĤãĤĬ
    0.09
    éľĦ
    0.09
    IEL
    0.08
    erer
    0.08
     roof
    0.08
    顺便
    0.08
    ç¾ģ
    0.08
    .Lib
    0.08
     roofs
    0.08
    Activations Density 0.051%

    No Known Activations