© 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. 19625
    Prev
    Next
    INDEX
    Explanations

    by the time

    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
    åĮĻ
    -0.10
    çĭİ
    -0.09
    箧
    -0.09
    plier
    -0.09
    æĽ´èĥ½
    -0.09
    毫ä¸įçĬ¹è±«
    -0.09
    ãģªãĤĬ
    -0.09
    æĸ¯å¡Ķ
    -0.09
    ä»İæѤ
    -0.08
    estre
    -0.08
    POSITIVE LOGITS
    å°ıå¿ĥ翼翼
    0.10
    æİ¥åĪ°
    0.09
    ward
    0.09
    gor
    0.09
    åĬłä¹ĭ
    0.08
    大åѦæ¯ķä¸ļ
    0.08
    gb
    0.08
    åĪ°è¾¾
    0.08
    agar
    0.08
    å»
    0.08
    Activations Density 0.004%

    No Known Activations