© 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. 1606
    Prev
    Next
    INDEX
    Explanations

    cutting, marking, boring, or trimming

    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
    CACHE
    -0.26
    _latest
    -0.24
    -fw
    -0.24
    quals
    -0.23
    imit
    -0.23
     Beat
    -0.23
    Clickable
    -0.22
     ÑĦон
    -0.22
     spokeswoman
    -0.22
     ÑĢазвива
    -0.22
    POSITIVE LOGITS
    åĪĩåī²
    0.40
     epoxy
    0.39
     cutting
    0.36
    尺寸
    0.33
    åĪĥ
    0.32
     Cutting
    0.32
     trimming
    0.32
    å°º
    0.32
     weld
    0.31
    åīª
    0.31
    Activations Density 0.044%

    No Known Activations