© 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. 63465
    Prev
    Next
    INDEX
    Explanations

    competition, competitors, competing

    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
    MAL
    -0.10
    acro
    -0.09
    æĬ½
    -0.09
    mia
    -0.09
     MAL
    -0.09
     irres
    -0.08
    .tw
    -0.08
    uries
    -0.08
    tweets
    -0.08
    å´ĩ
    -0.08
    POSITIVE LOGITS
    ç«ŀäºī对æīĭ
    0.36
    ç«ŀäºī
    0.29
     competitors
    0.27
    çļĦç«ŀäºī
    0.26
     competitor
    0.25
    競çĪŃ
    0.24
    对æīĭ
    0.24
     competition
    0.22
     rivals
    0.22
    ç«ŀ
    0.22
    Activations Density 0.093%

    No Known Activations