© 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. 2052
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions/nouns

    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
     specifically
    -0.37
     ultimately
    -0.36
    åħ·ä½ĵæĥħåĨµ
    -0.35
     essentially
    -0.34
     basically
    -0.34
     really
    -0.32
     realmente
    -0.31
     frankly
    -0.31
     ÑģобÑģÑĤвенно
    -0.30
     necessarily
    -0.30
    POSITIVE LOGITS
     (>
    0.24
    æĬķåħ¥åĪ°
    0.23
    ãģ¨ãģĦãģ£ãģŁ
    0.21
    olland
    0.21
    éĺĸ
    0.20
    åıĤä¸İåĪ°
    0.20
    æĪIJ为ä¸Ģ个
    0.20
     Bs
    0.20
    æ¯ıä¸Ģ个人
    0.20
     attain
    0.19
    Activations Density 0.628%

    No Known Activations