© 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. 551
    Prev
    Next
    INDEX
    Explanations

    coffee, drinks, sandwiches

    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
    éŁŃèıľ
    -0.24
    edly
    -0.24
     кÑĢай
    -0.23
    rena
    -0.23
    msp
    -0.23
    eut
    -0.23
     Hate
    -0.22
    indle
    -0.22
    istrate
    -0.22
    tml
    -0.22
    POSITIVE LOGITS
     complimentary
    0.30
     supplies
    0.29
     sourcing
    0.27
    æıIJä¾Ľ
    0.26
     kit
    0.26
    OnInit
    0.26
    enes
    0.25
    åħ¨å¥Ĺ
    0.25
     provision
    0.25
     available
    0.24
    Activations Density 0.009%

    No Known Activations