© 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. 52255
    Prev
    Next
    INDEX
    Explanations

    promotional products and printed items

    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
    COPY
    -0.09
    æľŁåĨħ
    -0.09
    åĭĻ
    -0.09
    æĦĪ
    -0.08
    ANGO
    -0.08
    è¾Ł
    -0.08
    çł
    -0.08
    åħ¸
    -0.08
    urrent
    -0.08
     sweep
    -0.08
    POSITIVE LOGITS
    åħµé©¬
    0.10
    çĹĺ
    0.09
    enc
    0.09
    é¦ĸæī¹
    0.09
    åĨįä¹Łæ²¡æľī
    0.08
    êµ°
    0.08
    çĶ³æĬ¥
    0.08
    ä¸ĢæĿ¡é¾Ļ
    0.08
     Mak
    0.08
    achi
    0.08
    Activations Density 0.015%

    No Known Activations