© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    names ending in -ers and -ings

    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
    åĨľå®¶
    -0.29
    èĢģ人家
    -0.27
     Huffman
    -0.27
    undy
    -0.25
     Cunning
    -0.25
    æģŃæķ¬
    -0.25
    è®®åijĺ
    -0.24
     GraphQL
    -0.23
    èĤ¡ä¸ľå¤§ä¼ļ
    -0.23
    ugi
    -0.23
    POSITIVE LOGITS
    åĩºè¡Ģ
    0.30
    溺
    0.29
    æŀª
    0.28
    çĩĥ
    0.27
    æĦı大åĪ©
    0.27
    æļ´åĬĽ
    0.26
     blasting
    0.26
     flaming
    0.26
    Jet
    0.26
     fiery
    0.25
    Activations Density 0.055%

    No Known Activations