© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    search and investigation

    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
     hypocrisy
    -0.30
     defaults
    -0.28
     democrat
    -0.26
    å´ĩå°ļ
    -0.24
     rebell
    -0.24
     norm
    -0.24
    _decor
    -0.24
    å¥Ń
    -0.24
     capitalism
    -0.24
     bucks
    -0.24
    POSITIVE LOGITS
    线索
    0.51
    çĸijä¼¼
    0.36
     sightings
    0.36
    IJľç´¢
    0.36
    æIJľç´¢
    0.35
    åı¯çĸij
    0.35
     suspected
    0.34
     unsuccessful
    0.34
     search
    0.33
     searching
    0.33
    Activations Density 0.065%

    No Known Activations