© 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. 1922
    Prev
    Next
    INDEX
    Explanations

    occupational safety and health administration

    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
    fy
    -0.26
    buch
    -0.24
    utory
    -0.23
    pulse
    -0.23
    CharCode
    -0.22
    pst
    -0.21
     jewellery
    -0.21
     setActive
    -0.21
    Soph
    -0.21
    bones
    -0.21
    POSITIVE LOGITS
    å½ĵå±Ģ
    0.24
    elon
    0.23
    常说
    0.23
    å§Ķåijĺ
    0.22
     Jim
    0.22
     authoritative
    0.22
    deo
    0.21
     H
    0.21
    æ§Ľ
    0.21
    èģĶåIJĪä¼ļ
    0.21
    Activations Density 0.002%

    No Known Activations