© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    agreement or confirmation

    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
    å°º
    -0.24
    üb
    -0.23
    ologna
    -0.23
    åįĹå±±
    -0.23
    ä»įæľª
    -0.22
    Pale
    -0.22
    ä¹ĭæĺŁ
    -0.21
    å«ļ
    -0.21
    óc
    -0.21
    çļĦåĨ³å¿ĥ
    -0.21
    POSITIVE LOGITS
    åĽŀäºĭ
    0.28
    éļ¾æĢª
    0.25
     Strength
    0.25
     strength
    0.24
    cher
    0.24
    apy
    0.24
     confirmed
    0.24
     confirming
    0.23
    ily
    0.22
    å®ŀåĬĽ
    0.22
    Activations Density 0.042%

    No Known Activations