© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2646
    Prev
    Next
    INDEX
    Explanations

    valley, port, county, sound, marsh, avenue

    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
    riendly
    -0.26
    çŁŃæľŁåĨħ
    -0.25
    çĪ¨
    -0.24
    åIJĦéĥ¨éŨ
    -0.24
    çļĦèµĦéĩij
    -0.24
    pecific
    -0.23
    åĴĮ个人
    -0.21
    åľ¨ä¸Ģ个
    -0.21
    è¤Ĭ
    -0.21
    侨
    -0.21
    POSITIVE LOGITS
    ç¤ģ
    0.26
    Triangle
    0.26
     Islands
    0.26
    å±±èĦī
    0.26
    dale
    0.24
     Peninsula
    0.24
     triangle
    0.24
     Triangle
    0.24
    夫人
    0.24
    å³°ä¼ļ
    0.24
    Activations Density 0.105%

    No Known Activations