© 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. 949
    Prev
    Next
    INDEX
    Explanations

    dataframe or df

    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
    ../
    -0.22
    olas
    -0.22
    quist
    -0.21
     lẽ
    -0.20
    Dick
    -0.20
    odash
    -0.20
    stone
    -0.20
     proceeding
    -0.20
    lear
    -0.19
    æĬķ注
    -0.19
    POSITIVE LOGITS
    -sided
    0.28
    alto
    0.20
     Alejandro
    0.19
    hips
    0.19
     кÑĢай
    0.19
    è¡ħ
    0.19
     rozp
    0.18
    bez
    0.18
    è¾¹ä¸Ĭ
    0.18
    eler
    0.18
    Activations Density 0.077%

    No Known Activations