© 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. 1981
    Prev
    Next
    INDEX
    Explanations

    products and services

    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
     INC
    -0.24
    工信éĥ¨
    -0.24
    è¾Ī
    -0.23
    sez
    -0.23
    -inc
    -0.22
    éĩįå¤į
    -0.22
    Representation
    -0.22
    ndef
    -0.22
     бо
    -0.21
    UGH
    -0.21
    POSITIVE LOGITS
    ç³»åĪĹ
    0.34
    lite
    0.33
    ç³»åĪĹ产åĵģ
    0.32
     series
    0.31
    ®
    0.28
    (TM
    0.28
    âĦ¢
    0.28
     lite
    0.27
     support
    0.27
    æĶ¯æĮģ
    0.26
    Activations Density 0.139%

    No Known Activations