© 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. 36929
    Prev
    Next
    INDEX
    Explanations

    take to describing action

    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
    éĶĻè¿ĩäºĨ
    -0.10
    åįģä¸ĩ
    -0.10
    tro
    -0.10
    æĥ³ä¸įåĪ°
    -0.09
    è´»
    -0.09
    ataka
    -0.09
    大éĥ¨åĪĨ人
    -0.09
    .fx
    -0.09
    agua
    -0.09
    æ³±
    -0.09
    POSITIVE LOGITS
    eam
    0.08
     promot
    0.08
     Internet
    0.08
    urn
    0.08
    人æ°Ķ
    0.08
    大è¡Ĺ
    0.08
    оÑī
    0.07
     Enlight
    0.07
    å¸ĤåľºçļĦ
    0.07
    RV
    0.07
    Activations Density 0.004%

    No Known Activations