© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 159
    Prev
    Next
    INDEX
    Explanations

    Ke

    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
    ãģĹãģ¾ãģĨ
    -0.33
    ally
    -0.28
    ed
    -0.26
    ness
    -0.22
    sWith
    -0.20
    å¹Ħ
    -0.19
    aire
    -0.18
    ../../../
    -0.18
    anza
    -0.18
    cake
    -0.18
    POSITIVE LOGITS
    íģ¼
    0.21
     behalf
    0.21
    -song
    0.20
    ãģĹãĤĩãģĨ
    0.20
     nug
    0.19
    egan
    0.19
    ên
    0.18
    appropri
    0.18
    /disable
    0.18
    strap
    0.18
    Activations Density 0.215%

    No Known Activations