© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    è¡įçĶŁ
    -0.36
     national
    -0.33
    æĻ®éģį
    -0.32
    诸å¤ļ
    -0.32
     arguably
    -0.32
     sanctioned
    -0.31
     charismatic
    -0.30
    è¿Ħä»Ĭ
    -0.30
     mainstream
    -0.30
     pioneering
    -0.30
    POSITIVE LOGITS
    çĶ¨æīĭ
    0.41
     preferably
    0.41
    æĶ¾åħ¥
    0.41
    åıĸåĩº
    0.39
    å®ĮæĪIJåIJİ
    0.38
    åĢĴåħ¥
    0.37
    è½»è½»åľ°
    0.36
    轻轻
    0.36
    çĦ¶åIJİ
    0.35
    çĦ¶åIJİåĨį
    0.35
    Activations Density 0.033%

    No Known Activations