© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    chewing and munching

    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
    tero
    -0.25
     bapt
    -0.23
    ä¸įæĺİ
    -0.22
     measures
    -0.21
    åıµ
    -0.20
     race
    -0.20
     births
    -0.20
     меÑĢ
    -0.20
    вид
    -0.19
    /black
    -0.19
    POSITIVE LOGITS
    åļ¼
    0.37
     cud
    0.32
    éĽ¶é£Ł
    0.31
    åĴĢ
    0.28
    sticks
    0.27
     habits
    0.26
     chewing
    0.26
    bone
    0.25
    hoe
    0.24
    /sn
    0.23
    Activations Density 0.011%

    No Known Activations