© 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. 52654
    Prev
    Next
    INDEX
    Explanations

    computer network, power outage, TV channel

    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
    oil
    -0.09
    éļį
    -0.09
    åĴĮå°ļ
    -0.09
    езд
    -0.09
    ç³Ĺ
    -0.09
    åĽ½éģĵ
    -0.08
    çĶµåı°
    -0.08
    èħķ
    -0.08
    çĽ¸äº²
    -0.08
    åľ¨çİ°åľº
    -0.08
    POSITIVE LOGITS
    .ylim
    0.09
    -motion
    0.08
     lan
    0.08
    instein
    0.08
    çIJĨè´¢
    0.08
    ennen
    0.08
    å¾Ħ
    0.08
     Neighborhood
    0.08
    .dsl
    0.08
    ź
    0.07
    Activations Density 0.187%

    No Known Activations