© 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. 37126
    Prev
    Next
    INDEX
    Explanations

    disclaimers, instructions

    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
    enic
    -0.10
    æĨİ
    -0.09
     Blair
    -0.09
    ç§ĥ
    -0.08
    ç½ijå°ıç¼ĸ
    -0.08
    éķĢ
    -0.08
    én
    -0.08
    lane
    -0.08
    è¡°
    -0.08
    arning
    -0.08
    POSITIVE LOGITS
    两åIJį
    0.10
    ingo
    0.09
    ç½®äºİ
    0.09
    å®łçī©
    0.09
    NPC
    0.09
     pets
    0.08
    åĭ¿
    0.08
    åĹĮ
    0.08
    indr
    0.08
    çı
    0.08
    Activations Density 0.005%

    No Known Activations