© 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. 5880
    Prev
    Next
    INDEX
    Explanations

    Mojibake and encoding issues

    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
    imson
    -0.10
    มà¸Ļ
    -0.09
    ä¸įéĢļ
    -0.09
    讲座
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    æł¹æį®èĩªå·±
    -0.09
    èĶ¼
    -0.09
    æ³Ĭ
    -0.08
    olls
    -0.08
    asthan
    -0.08
    POSITIVE LOGITS
    Ñģло
    0.08
    åį°è±¡æ·±åĪ»
    0.08
    çļĦæł¹æľ¬
    0.08
    uda
    0.08
    çıŃ级
    0.08
    æī¹åĩĨ
    0.08
    å°±åĮ»
    0.08
    emente
    0.08
    apro
    0.08
    çĤ¹å¤ļ
    0.08
    Activations Density 0.003%

    No Known Activations