© 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. 8003
    Prev
    Next
    INDEX
    Explanations

    society followed by organizational modifiers

    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
    饰
    -0.09
    cept
    -0.08
    uar
    -0.08
    亲æīĭ
    -0.08
    .Stretch
    -0.08
     Dor
    -0.08
    ä½ĵ系建设
    -0.08
    roads
    -0.08
     Marian
    -0.08
    pread
    -0.07
    POSITIVE LOGITS
    ми
    0.10
    ftware
    0.10
    ieten
    0.10
    ä¸ŃåĽ½åĪ¶éĢł
    0.09
    avery
    0.09
    å¥Ħ
    0.09
    æ¨Ĺ
    0.09
    гÑĥ
    0.09
    .publisher
    0.09
    illing
    0.09
    Activations Density 0.017%

    No Known Activations