© 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. 8093
    Prev
    Next
    INDEX
    Explanations

    extra or additional

    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
    кÑģ
    -0.10
    ussen
    -0.10
    èįĥ
    -0.09
    zas
    -0.09
    Prototype
    -0.09
    åĪ©çĶ¨çİĩ
    -0.09
    家å±ŀ
    -0.08
    actly
    -0.08
    åħ·ä½ĵæĥħåĨµ
    -0.08
    çĶ¨éĩı
    -0.08
    POSITIVE LOGITS
    /right
    0.11
     few
    0.10
    sworth
    0.10
     layer
    0.09
    æĤĦ
    0.09
    icit
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    åįģä½Ļ
    0.09
    ä¿©
    0.09
     yOffset
    0.09
    Activations Density 0.013%

    No Known Activations