© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32110
    Prev
    Next
    INDEX
    Explanations

    nicknames or titles

    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
    iali
    -0.10
    é³ŀ
    -0.09
    å«©
    -0.09
    æŃ£åĢ¼
    -0.09
    åİŁæľ¬
    -0.09
    åħ¨èµĦ
    -0.09
    à¸ķำ
    -0.09
    æµģè¡Į
    -0.09
    Vintage
    -0.09
    æľĢæĸ°
    -0.09
    POSITIVE LOGITS
    被称为
    0.11
    被èªī为
    0.11
    åıĪ称
    0.09
    åı·ç§°
    0.09
    åĽłä¸ºæĪij们
    0.09
    _MAGIC
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.08
    bread
    0.08
     referred
    0.08
    akedown
    0.08
    Activations Density 0.087%

    No Known Activations