© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1517
    Prev
    Next
    INDEX
    Explanations

    memory and recall

    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
    ares
    -0.25
    ries
    -0.24
    prises
    -0.23
    noise
    -0.23
     brief
    -0.23
    é£İ鼨
    -0.23
    æĹ¢æľī
    -0.22
    å¤įå·¥
    -0.22
    apan
    -0.21
    ReLU
    -0.21
    POSITIVE LOGITS
     memor
    0.37
     pitch
    0.31
     Memor
    0.29
    -memory
    0.28
     memory
    0.26
    诵
    0.25
     chunks
    0.25
    Pitch
    0.25
    æĨ¶
    0.24
    (mem
    0.24
    Activations Density 0.018%

    No Known Activations