© 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. 52209
    Prev
    Next
    INDEX
    Explanations

    deliberately or elaborate

    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
    lify
    -0.11
    hoot
    -0.10
    imal
    -0.09
    amp
    -0.09
    finder
    -0.09
    itional
    -0.09
    manship
    -0.09
    ä¸įæĸŃåıijå±ķ
    -0.09
    å¾·æĭī
    -0.09
    ãĤ£
    -0.08
    POSITIVE LOGITS
    <<<<
    0.10
    anc
    0.09
    ively
    0.09
    edException
    0.09
    ately
    0.09
    -minded
    0.09
    gings
    0.09
    å¾Īæ¸ħæ¥ļ
    0.09
    ATION
    0.08
    ties
    0.08
    Activations Density 0.009%

    No Known Activations