© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51463
    Prev
    Next
    INDEX
    Explanations

    Gmail and related actions

    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
    arding
    -0.09
    ILL
    -0.08
    _mount
    -0.08
    çĵ¦
    -0.08
    ht
    -0.08
    ate
    -0.08
    ss
    -0.08
    ä¸Ģå¤Ħ
    -0.07
    大çīĩ
    -0.07
    AIM
    -0.07
    POSITIVE LOGITS
    pline
    0.09
    ietf
    0.09
    ä¸įä¸Ĭ
    0.09
    éĤ®ç®±
    0.09
    mers
    0.09
    ously
    0.09
     sạn
    0.09
    鸥
    0.09
    wich
    0.09
    åľ¨åĽ½åĨħ
    0.09
    Activations Density 0.008%

    No Known Activations