© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    holding, grip, and pull actions

    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
    +xml
    -0.27
     compil
    -0.24
    å±ķ示
    -0.24
    éĢģ
    -0.23
    æıŃéľ²
    -0.23
    个æĢ§
    -0.23
    éľ°
    -0.23
    æĽĿ
    -0.22
    èµ°åħ¥
    -0.22
    ilog
    -0.21
    POSITIVE LOGITS
     gripping
    0.33
    anchor
    0.33
     anchor
    0.32
     anch
    0.31
    çī¢åĽº
    0.31
     anchors
    0.31
     grip
    0.30
     Grip
    0.30
    æĶ¯æĴij
    0.30
    æĬĬæĮģ
    0.30
    Activations Density 0.027%

    No Known Activations