© 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. 9062
    Prev
    Next
    INDEX
    Explanations

    search results: or matching

    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
    PropertyDescriptor
    -0.09
     Canyon
    -0.09
    æĹ©
    -0.09
    èĦĸåŃIJ
    -0.09
     Tig
    -0.09
    WindowState
    -0.09
    ValuePair
    -0.08
    _integer
    -0.08
    ItemAt
    -0.08
    泡泡
    -0.08
    POSITIVE LOGITS
    å¾Ĵ
    0.11
    飬
    0.10
    åįģéĩĮ
    0.09
    åIJĥåĪ°
    0.08
    kte
    0.08
    active
    0.08
    éģµ
    0.08
    綦
    0.08
     Fre
    0.08
    ä¿Ŀå®Ī
    0.08
    Activations Density 0.046%

    No Known Activations