© 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. 916
    Prev
    Next
    INDEX
    Explanations

    suitable for

    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
    ieme
    -0.24
    åij½ä¸Ń
    -0.24
    umed
    -0.23
     indem
    -0.23
    oft
    -0.22
    thon
    -0.22
    ource
    -0.22
    abouts
    -0.22
    aths
    -0.21
    /stats
    -0.21
    POSITIVE LOGITS
    æĸ°æĹ¶æľŁ
    0.27
    æĸ°æĹ¶ä»£
    0.26
    驾é©Ń
    0.26
    严èĤĥ
    0.25
     beginners
    0.25
     conveying
    0.25
    éķ¿è¿ľ
    0.25
     use
    0.25
    çĶ¨æĿ¥
    0.25
    åĽ½æĥħ
    0.25
    Activations Density 0.070%

    No Known Activations