© 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. 9077
    Prev
    Next
    INDEX
    Explanations

    calorie counting, diets, energy

    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
    ness
    -0.11
    ðŁı»
    -0.09
     Beste
    -0.09
    tlement
    -0.09
    èĭŀ
    -0.08
    ä¸įäºĨ
    -0.08
    chg
    -0.08
    ward
    -0.08
    ancial
    -0.08
    ABB
    -0.08
    POSITIVE LOGITS
    ary
    0.10
    ous
    0.10
    arity
    0.09
    æ®Ĩ
    0.09
    enda
    0.09
    ä¸ĩ象
    0.09
    antar
    0.09
    WISE
    0.08
    æĥĬ人
    0.08
    phe
    0.08
    Activations Density 0.006%

    No Known Activations