© 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. 218
    Prev
    Next
    INDEX
    Explanations

    base class

    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
    åı¦ä¸ĢåįĬ
    -0.30
    assy
    -0.24
    _SECTION
    -0.24
     nit
    -0.23
     qualified
    -0.23
    磬
    -0.22
    åı¦ä¸Ģç§į
    -0.22
    åħ¥çĿ¡
    -0.21
    PATH
    -0.21
    atum
    -0.21
    POSITIVE LOGITS
    绣ä¸Ģ
    0.54
    åħ¨å±Ģ
    0.45
    绣
    0.43
     unified
    0.43
     unify
    0.42
    绣çŃ¹
    0.42
     overarching
    0.40
     centralized
    0.40
     umbrella
    0.39
    åħ¨åĽ½
    0.38
    Activations Density 0.543%

    No Known Activations