© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    I, we, God, do, is

    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
    tape
    -0.24
    _UNIQUE
    -0.23
    jo
    -0.23
    iri
    -0.22
    éĥ½èĥ½å¤Ł
    -0.22
     calend
    -0.22
    Characters
    -0.21
    Cycle
    -0.21
    unicode
    -0.21
    (pthread
    -0.20
    POSITIVE LOGITS
    æľķ
    0.26
    æĪijçİ°åľ¨
    0.25
     dock
    0.24
    ç«Ł
    0.24
     mine
    0.24
    udy
    0.24
    æĪijæīį
    0.23
     haste
    0.23
     thou
    0.23
    วà¸Ķ
    0.23
    Activations Density 0.016%

    No Known Activations