© 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. 1364
    Prev
    Next
    INDEX
    Explanations

    mineral and related compounds

    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
    steam
    -0.25
     Gujar
    -0.23
    łģ
    -0.22
    çĤ«
    -0.22
     Steam
    -0.22
    å¥ĸéĩij
    -0.21
    大æ´ĭ
    -0.21
    à¤ħ
    -0.21
    tre
    -0.21
     Ä°nt
    -0.21
    POSITIVE LOGITS
    å°Ŀ
    0.22
    æĸ°å¸¸æĢģ
    0.21
    enqueue
    0.21
    fcn
    0.21
    akit
    0.21
    (QtCore
    0.21
    etty
    0.21
    izedName
    0.20
    Invoke
    0.20
    æķĪåĬĽ
    0.20
    Activations Density 0.001%

    No Known Activations