© 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. 179
    Prev
    Next
    INDEX
    Explanations

    events, contests, and elections

    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
    ATAR
    -0.23
     comida
    -0.22
    vertise
    -0.22
    otime
    -0.21
    ieren
    -0.21
    ä¸Ģåı£
    -0.21
    APON
    -0.20
    麻çĹ¹
    -0.20
    ephir
    -0.20
    ocz
    -0.20
    POSITIVE LOGITS
     aforementioned
    0.32
    -century
    0.31
    -born
    0.26
     largest
    0.26
    -generation
    0.26
    -largest
    0.25
     hottest
    0.24
     longest
    0.24
    -scale
    0.23
     highest
    0.23
    Activations Density 0.088%

    No Known Activations