© 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. 694
    Prev
    Next
    INDEX
    Explanations

    compression, reduction, size, storage, amount

    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
    engers
    -0.24
    çķı
    -0.23
     pulse
    -0.23
    QE
    -0.23
    assa
    -0.23
    pulse
    -0.22
     rush
    -0.21
    .delivery
    -0.21
     action
    -0.21
    æ²»å®ī
    -0.21
    POSITIVE LOGITS
    åİĭ缩
    0.35
     compress
    0.35
    åĩıå°ij
    0.35
    èĬĤ约
    0.35
     reduces
    0.34
    èĬĤçľģ
    0.34
    åĩıå°ijäºĨ
    0.34
     reductions
    0.32
    compression
    0.32
     reduce
    0.32
    Activations Density 0.134%

    No Known Activations