© 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. 6482
    Prev
    Next
    INDEX
    Explanations

    largely followed by verbs/prepositions

    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
    ç´¯äºĨ
    -0.09
    รา
    -0.09
    íķ¸
    -0.09
    sei
    -0.08
    ted
    -0.08
    ãģĹãĤĩãģĨ
    -0.08
     cru
    -0.08
    ech
    -0.08
    çľģæĶ¿åºľ
    -0.08
    رÙĪ
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.12
    éĽĨä¸Ńåľ¨
    0.11
    å¾ĹçĽĬäºİ
    0.10
    à¹Į
    0.10
    离ä¸įå¼Ģ
    0.10
    stone
    0.09
    onne
    0.09
    æĪIJè´¥
    0.09
    fully
    0.09
    itmap
    0.09
    Activations Density 0.010%

    No Known Activations