© 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. 20875
    Prev
    Next
    INDEX
    Explanations

    large or small containers

    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
    Ò®
    -0.09
    çĬ¶åħĥ
    -0.09
    å°ıåŃIJ
    -0.09
    ailable
    -0.09
    æľ¬äºº
    -0.09
    ruc
    -0.08
    eneg
    -0.08
    åIJĦèĩªçļĦ
    -0.08
    ÑĢажа
    -0.08
    æĹºçĽĽ
    -0.08
    POSITIVE LOGITS
     Spears
    0.10
    ç£ĭ
    0.08
    Ëĭ
    0.08
    å¤Ł
    0.08
    å¿Ń
    0.08
    alic
    0.08
    çĪ±ç¾İ
    0.08
     clock
    0.07
    ç¢Ĺ
    0.07
    ouri
    0.07
    Activations Density 0.004%

    No Known Activations