© 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. 611
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    olle
    -0.27
     latter
    -0.23
     Bhar
    -0.23
    mail
    -0.22
    åŀĴ
    -0.22
    Hol
    -0.21
    urve
    -0.20
    åľ³
    -0.20
     rop
    -0.20
    åIJİèĢħ
    -0.20
    POSITIVE LOGITS
    æĻ®æŁ¥
    0.24
    -prefix
    0.23
    -based
    0.23
    Registrar
    0.23
    inary
    0.21
    çĶŃ
    0.21
    èĢģ大
    0.21
    ary
    0.21
    åĵī
    0.20
    -columns
    0.20
    Activations Density 0.000%

    No Known Activations