© 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. 52020
    Prev
    Next
    INDEX
    Explanations

    you think

    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
    Õ®
    -0.09
    ìĤ¬ëĬĶ
    -0.09
    ç¥Ģ
    -0.08
    åıĹ害人
    -0.08
    alo
    -0.08
    _po
    -0.08
    .syntax
    -0.08
    yre
    -0.08
    ku
    -0.08
    .RecyclerView
    -0.08
    POSITIVE LOGITS
    ä½łä»¥ä¸º
    0.10
    侥幸
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    ä»ħä»ħæĺ¯
    0.09
    éĩijéĻµ
    0.09
    åıªæĺ¯
    0.09
    .getLocal
    0.09
    Singleton
    0.08
    ева
    0.08
    ipy
    0.08
    Activations Density 0.022%

    No Known Activations