© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1264
    Prev
    Next
    INDEX
    Explanations

    shared facilities, resources, goals, development, responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    SHARE
    -0.26
    othy
    -0.25
    eba
    -0.23
    åĪĨ享
    -0.23
    åĴĮæĶ¯æĮģ
    -0.23
    oz
    -0.23
    aries
    -0.22
    sharing
    -0.21
    å¿ĥå¾Ĺ
    -0.21
    åħ·ä½ĵåĨħ容
    -0.21
    POSITIVE LOGITS
    /non
    0.23
    /static
    0.23
    æĢ§å¼º
    0.22
     Bolt
    0.21
    -com
    0.20
    -language
    0.20
    plate
    0.19
     collo
    0.19
    *
    0.19
     or
    0.19
    Activations Density 0.013%

    No Known Activations