© 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. 529
    Prev
    Next
    INDEX
    Explanations

    price and free downloads

    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
    andest
    -0.25
     plateau
    -0.24
    å¸ĥç½®
    -0.23
    Rand
    -0.22
    Noise
    -0.22
    /front
    -0.22
    å¯Įè£ķ
    -0.21
    ä¸ĢäºĮ
    -0.21
    overlap
    -0.21
    =center
    -0.21
    POSITIVE LOGITS
     downloads
    0.30
     Launch
    0.29
     scrolling
    0.27
     iTunes
    0.26
    éĢļè¡Įè¯ģ
    0.26
     Downloads
    0.25
    eware
    0.25
    çļĦè®°å¿Ĩ
    0.24
     Shank
    0.24
    âĢ
    0.23
    Activations Density 0.009%

    No Known Activations