© 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. 2565
    Prev
    Next
    INDEX
    Explanations

    decade ago or later

    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
    ness
    -0.21
    ses
    -0.21
    bidden
    -0.21
    sing
    -0.21
    inden
    -0.20
    inese
    -0.20
    /disable
    -0.20
    å½ĵå±Ģ
    -0.19
    san
    -0.19
    imon
    -0.19
    POSITIVE LOGITS
     ago
    0.35
    -long
    0.35
    -span
    0.31
    ãģ¶ãĤĬ
    0.28
    -old
    0.27
    以æĿ¥
    0.26
    å·²ä¹ħçļĦ
    0.25
    以ä¾Ĩ
    0.24
    /year
    0.24
    -plus
    0.24
    Activations Density 0.013%

    No Known Activations