© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    in the past

    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
    èĬĿ
    -0.26
    née
    -0.26
    åħ¼
    -0.26
    并éĢļè¿ĩ
    -0.24
    [^
    -0.23
    {*
    -0.23
    ONA
    -0.23
    Rather
    -0.23
    并åIJij
    -0.23
    å°ijéĩı
    -0.22
    POSITIVE LOGITS
    åħij
    0.22
    âĢ¦
    0.22
     reel
    0.21
     пÑĢекÑĢаÑģн
    0.21
     IID
    0.20
     Brew
    0.20
    _deposit
    0.20
    çķ¶æĤ¨åľ¨
    0.20
    .ResumeLayout
    0.20
     revolution
    0.20
    Activations Density 0.287%

    No Known Activations