© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37998
    Prev
    Next
    INDEX
    Explanations

    childhood and age groups

    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
    olib
    -0.10
    linger
    -0.09
    eel
    -0.09
    æĥ®
    -0.09
    à¹ģà¸Ĺ
    -0.09
    èĵŁ
    -0.09
    ema
    -0.09
     entirety
    -0.08
    æĸĭ
    -0.08
    å¦ĤæĦı
    -0.08
    POSITIVE LOGITS
    hood
    0.10
    ðŁı»
    0.09
    -friendly
    0.09
    -aged
    0.09
    æĹ¶æľŁçļĦ
    0.09
    åħ
    0.08
    Republic
    0.08
    æľŁ
    0.08
     Friendly
    0.08
    .LayoutParams
    0.08
    Activations Density 0.016%

    No Known Activations