© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51833
    Prev
    Next
    INDEX
    Explanations

    flush or wash

    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
    äºİæŃ¤
    -0.09
     scri
    -0.09
    odge
    -0.09
    èħ°
    -0.08
    .deep
    -0.08
    UNCT
    -0.08
    aser
    -0.08
    oda
    -0.08
    顽
    -0.08
    _SAFE
    -0.08
    POSITIVE LOGITS
     Flush
    0.13
    flush
    0.12
    Flush
    0.12
     flush
    0.11
     flushed
    0.11
    æ»ĭåij³
    0.10
    æİī
    0.10
    æ´Ĺ礼
    0.10
     flushing
    0.10
    æİīäºĨ
    0.10
    Activations Density 0.035%

    No Known Activations