© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53016
    Prev
    Next
    INDEX
    Explanations

    dice rolls

    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
    -secondary
    -0.09
    resses
    -0.09
    éĻ¶
    -0.09
    åįĬå¤ľ
    -0.09
    飦
    -0.08
    è´«
    -0.08
    è§ģè¯Ĩ
    -0.08
    secondary
    -0.08
    _blob
    -0.08
    ç»Ī身
    -0.08
    POSITIVE LOGITS
    kit
    0.10
    úng
    0.10
    å°ģéĿ¢
    0.10
    骰
    0.10
    eter
    0.09
    ä¸Ģæŀ¶
    0.09
    æĺ¯ä¸įæĺ¯
    0.09
     ë§ŀ
    0.08
    å±Ģéķ¿
    0.08
    ä¸ĭå±ŀ
    0.08
    Activations Density 0.023%

    No Known Activations