© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating completion and outcomes

    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
    æŁ¥çľĭæĽ´å¤ļ
    -0.25
     ..."↵↵
    -0.22
     ..."↵
    -0.21
    æľ«
    -0.21
    arium
    -0.21
     vir
    -0.21
    setData
    -0.21
    ovel
    -0.21
    缸å½ĵ
    -0.20
    åĦ¿
    -0.20
    POSITIVE LOGITS
    è¿ĩçļĦ
    0.25
     during
    0.25
    ä¸İåıijå±ķ
    0.24
    åħļæĢ»æĶ¯
    0.24
     parenthesis
    0.23
    during
    0.23
    ä¸İåIJ¦
    0.23
    /not
    0.23
    è¿ĩ大
    0.22
    owns
    0.21
    Activations Density 0.057%

    No Known Activations