© 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. 1655
    Prev
    Next
    INDEX
    Explanations

    designs by

    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
    DOT
    -0.25
     ÐŁÐ¾Ñĩем
    -0.23
    BAD
    -0.23
    åľĪ
    -0.22
    tons
    -0.21
     rather
    -0.21
    è¯ģ
    -0.21
    峿
    -0.21
    çĽĺ
    -0.21
    SED
    -0.20
    POSITIVE LOGITS
    ive
    0.23
    ogne
    0.22
     {?
    0.22
     Nurse
    0.21
    çļĦ年轻人
    0.21
     unto
    0.21
    ertools
    0.21
     Trouble
    0.20
     haha
    0.20
    ebin
    0.20
    Activations Density 0.750%

    No Known Activations