© 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. 7957
    Prev
    Next
    INDEX
    Explanations

    game or card specific keywords

    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
    erdem
    -0.09
    arris
    -0.09
    æĥ³åĥı
    -0.09
    æīĢè°ĵ
    -0.09
     intrusive
    -0.08
    éĽı
    -0.08
     intrusion
    -0.08
    .invalidate
    -0.08
    Trail
    -0.08
    _intf
    -0.08
    POSITIVE LOGITS
    çīĮ
    0.12
    幺
    0.10
     cards
    0.10
     card
    0.10
    ç¾ģ
    0.09
    cej
    0.09
    æĺ¯ä¸Ģ件
    0.09
     повеÑĢ
    0.09
    .nz
    0.09
    è§ij
    0.08
    Activations Density 0.039%

    No Known Activations