© 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. 57240
    Prev
    Next
    INDEX
    Explanations

    listed historic buildings and property

    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
    _present
    -0.09
    å¼ģ
    -0.08
    Newsletter
    -0.08
    _FM
    -0.08
    æģ¼
    -0.08
    ç®Ģæĺĵ
    -0.08
    çĶ¸
    -0.08
    ä¹į
    -0.08
    çĪ½
    -0.08
    çijľ
    -0.08
    POSITIVE LOGITS
    æĸĩçī©
    0.19
    æĸĩåĮĸéģĹ产
    0.16
    éģĹ迹
    0.14
    æĸĩçī©ä¿ĿæĬ¤
    0.13
    åįļçī©é¦Ĩ
    0.13
    éģĹ产
    0.13
    åİĨåı²
    0.13
    åİĨåı²æĸĩåĮĸ
    0.12
    èĢĥåı¤
    0.11
    à¹Ĥà¸ļราà¸ĵ
    0.11
    Activations Density 0.150%

    No Known Activations