© 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. 2075
    Prev
    Next
    INDEX
    Explanations

    freelance writer, journalist, editor

    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
    å¾Īæ¸ħæ¥ļ
    -0.25
    åįĩ级æĶ¹éĢł
    -0.25
    èĭ±åĭĩ
    -0.25
    èĤ©èĨĢ
    -0.25
    绢
    -0.24
    å°ĨåĨĽ
    -0.24
    åħļå§Ķ书记
    -0.24
    æĺĩ
    -0.24
    åįĩ
    -0.23
    rop
    -0.23
    POSITIVE LOGITS
     freelance
    0.42
     freelancer
    0.34
     Freel
    0.34
    åĨĻä½ľ
    0.32
     freel
    0.31
     Writers
    0.31
     Editing
    0.29
     writer
    0.28
     Writer
    0.28
    .Writer
    0.27
    Activations Density 0.031%

    No Known Activations