© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8620
    Prev
    Next
    INDEX
    Explanations

    filamentous hemagglutinin, pertactin

    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
    éľīç´ł
    -0.10
    æł½
    -0.10
    åģĩ
    -0.09
    _OW
    -0.09
    以èī²
    -0.09
    çĮ¿
    -0.09
    ocity
    -0.09
    åľ¨å®¶éĩĮ
    -0.08
    achu
    -0.08
    imas
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.10
    éĺIJ
    0.09
     viet
    0.09
    Scheduler
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    å¿Ĩ
    0.08
    çĮĬ
    0.08
    York
    0.07
    çijĹ
    0.07
    æ¢ĵ
    0.07
    Activations Density 0.016%

    No Known Activations