© 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. 7410
    Prev
    Next
    INDEX
    Explanations

    and [descriptive noun]

    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
    çļĦ主è¦ģ
    -0.10
    çļĦä½ľçĶ¨
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    .renderer
    -0.09
    çļĦåİŁåĽł
    -0.09
    类似çļĦ
    -0.09
    å´ĩ
    -0.09
    ception
    -0.09
    åĺ´éĩĮ
    -0.09
    çŃ²
    -0.09
    POSITIVE LOGITS
    iest
    0.09
    liest
    0.09
    ign
    0.09
    iem
    0.08
    unj
    0.08
    tep
    0.08
    unge
    0.08
     nature
    0.08
    un
    0.08
    do
    0.07
    Activations Density 0.184%

    No Known Activations