© 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. 2363
    Prev
    Next
    INDEX
    Explanations

    geological survey, interest, exploration, minerals

    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
    殿ä¸ĭ
    -0.23
    -Za
    -0.22
    éĴĿ
    -0.22
    èĪµ
    -0.22
     nghá»ĭ
    -0.21
    ople
    -0.21
    anness
    -0.21
    座æ¤ħ
    -0.20
    èıľ
    -0.20
     "="
    -0.20
    POSITIVE LOGITS
    åľ°è´¨
    0.55
     geological
    0.54
     Geological
    0.45
     minerals
    0.43
    å²©çŁ³
    0.41
    åŃ¦å®¶
    0.40
     mineral
    0.39
    éĩĩçŁ¿
    0.39
    çŁ¿çī©
    0.38
    åľ°è²Į
    0.36
    Activations Density 0.015%

    No Known Activations