© 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. 2645
    Prev
    Next
    INDEX
    Explanations

    numbers followed by unit

    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
    .Virtual
    -0.24
     advances
    -0.23
    >'č↵
    -0.22
    leo
    -0.22
    åĨł
    -0.22
     hạ
    -0.22
    äºĭæ¥Ń
    -0.21
    (lp
    -0.21
    æĭĸ
    -0.21
    onical
    -0.21
    POSITIVE LOGITS
     words
    0.31
     sentence
    0.31
    ä¸įè¶ħè¿ĩ
    0.29
     sentences
    0.28
    éĻIJåĪ¶
    0.28
    åı¥åŃIJ
    0.28
     paragraph
    0.28
    两åı¥
    0.28
    ä¸Ģåı¥
    0.28
    phrase
    0.28
    Activations Density 0.007%

    No Known Activations