© 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. 51948
    Prev
    Next
    INDEX
    Explanations

    not distributed or missing references

    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
    åĿª
    -0.10
    赢家
    -0.09
    _BIN
    -0.09
    é£ŀè·ĥ
    -0.09
    åĶ¿
    -0.09
    ileo
    -0.09
    èİŀ
    -0.09
    æĭ¾
    -0.09
    åıªè¦ģä½ł
    -0.09
    æ¤Ĵ
    -0.09
    POSITIVE LOGITS
    åĽłåľ°
    0.09
    çİ¢
    0.09
    ç±
    0.09
    æľ
    0.09
     Hod
    0.09
    itur
    0.08
    æĮ«æĬĺ
    0.08
    ushing
    0.08
     Anita
    0.08
    ustum
    0.08
    Activations Density 0.001%

    No Known Activations