© 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. 9600
    Prev
    Next
    INDEX
    Explanations

    describing function or state

    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
    å°ļ
    -0.09
    indi
    -0.08
    INED
    -0.08
    éĹªçĥģ
    -0.08
    ARING
    -0.08
    pping
    -0.08
    å¸ĮæľĽéĢļè¿ĩ
    -0.08
    eding
    -0.08
    indow
    -0.08
    енÑĭ
    -0.08
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.11
    åı¯è°ĵæĺ¯
    0.09
    å°±æĺ¯ä¸ºäºĨ
    0.09
    entifier
    0.09
    ä¼Ĭæĸ¯åħ°
    0.09
    驹
    0.09
    èī¯å¥½
    0.09
    å°±èĥ½å¤Ł
    0.08
    äºĨä¸Ģ份
    0.08
    äºĽä»Ģä¹Ī
    0.08
    Activations Density 0.675%

    No Known Activations