© 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. 69
    Prev
    Next
    INDEX
    Explanations

    city, country addresses

    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
    ativa
    -0.24
    æŃ¤æ¬¡
    -0.23
    deo
    -0.23
    亢
    -0.23
    ATAR
    -0.23
    çĸį
    -0.23
    Escape
    -0.23
    _DIP
    -0.22
    对该
    -0.22
     convict
    -0.22
    POSITIVE LOGITS
     Tem
    0.26
     Bid
    0.26
     Ful
    0.25
    ={$
    0.25
     Mile
    0.24
     USA
    0.24
     Bur
    0.23
     Urban
    0.23
     Kö
    0.23
     Kamp
    0.23
    Activations Density 0.011%

    No Known Activations