© 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. 37080
    Prev
    Next
    INDEX
    Explanations

    Alan

    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
    ening
    -0.15
    ened
    -0.13
    ler
    -0.10
    ably
    -0.10
    人家
    -0.09
    å·´å·´
    -0.09
    顽强
    -0.09
    elsen
    -0.08
    duc
    -0.08
    cribe
    -0.08
    POSITIVE LOGITS
    çĪ·
    0.12
    ìĤ¬íķŃ
    0.11
    éªĭ
    0.11
    ovo
    0.10
    ../
    0.10
    ãģĤãĤĭç¨ĭ度
    0.10
    ways
    0.10
    thon
    0.10
    _simps
    0.10
    <<<<<<<<
    0.09
    Activations Density 0.014%

    No Known Activations