© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    reinforce, strengthen, reinforcement

    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
     nir
    -0.25
    æĥĿ
    -0.23
    åĪĽéĢłæĢ§
    -0.22
     ResultSet
    -0.22
    çݯå¢ĥä¸Ń
    -0.21
    UAL
    -0.21
     curiosity
    -0.21
    رÙĬÙĥ
    -0.21
     Dich
    -0.21
     Environment
    -0.20
    POSITIVE LOGITS
    åĬłåĽº
    0.42
    strength
    0.33
    å¢ŀ强
    0.32
    èĸĦå¼±
    0.32
    _strength
    0.31
    硬åĮĸ
    0.31
     strengthened
    0.31
     reinforcement
    0.31
    å¢ŀ强äºĨ
    0.31
    åĿļåĽº
    0.30
    Activations Density 0.023%

    No Known Activations