© 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. 2079
    Prev
    Next
    INDEX
    Explanations

    rights not granted

    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
    tras
    -0.25
    å¿ĥæĦ¿
    -0.24
    wÅĤaÅĽciw
    -0.21
    tures
    -0.21
    tics
    -0.21
    ster
    -0.20
    uest
    -0.20
    tri
    -0.20
    天ä¸Ĭ
    -0.20
    tc
    -0.20
    POSITIVE LOGITS
    edly
    0.29
    FUL
    0.27
    ful
    0.27
    fulness
    0.25
    lessly
    0.23
    -bearing
    0.22
    atz
    0.22
     cookies
    0.21
    fully
    0.21
    APH
    0.21
    Activations Density 0.018%

    No Known Activations