© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    XML tags

    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
     Stern
    -0.23
     mere
    -0.22
    :host
    -0.22
    .currentIndex
    -0.21
    }}],↵
    -0.21
    IntPtr
    -0.21
     maintained
    -0.21
     onCreateView
    -0.21
    .apiUrl
    -0.21
     principalColumn
    -0.21
    POSITIVE LOGITS
    æĸĩæľ¬
    0.26
    æµģçķħ
    0.26
     DATA
    0.24
    0.24
    åıĸåĩº
    0.23
    Dump
    0.23
    é¢ĺ缮
    0.23
     Calculate
    0.23
    DATA
    0.22
    æķ´çIJĨ
    0.22
    Activations Density 0.023%

    No Known Activations