© 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. 1240
    Prev
    Next
    INDEX
    Explanations

    after 'in', 'left', 'I', 'that'

    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
    rary
    -0.22
     ấy
    -0.22
    ovsky
    -0.22
    ä¹İ
    -0.20
    serializer
    -0.20
    VERS
    -0.20
    MOVE
    -0.20
    AIL
    -0.20
     itself
    -0.20
    åIJ¯çĶ¨
    -0.20
    POSITIVE LOGITS
    -letter
    0.24
     survived
    0.22
    .types
    0.22
     bef
    0.21
     Rei
    0.21
    imits
    0.21
    å¿ĥæĦ¿
    0.21
    -byte
    0.20
     barely
    0.20
     chew
    0.20
    Activations Density 0.238%

    No Known Activations