© 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. 1239
    Prev
    Next
    INDEX
    Explanations

    volume units (gallons, litres)

    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
    elt
    -0.21
    è¾ĥ强
    -0.21
    etal
    -0.20
    etu
    -0.20
     vibr
    -0.19
    Fab
    -0.19
    éĺ³æĢ§
    -0.19
    place
    -0.19
    轨
    -0.19
    主ä¹ī
    -0.18
    POSITIVE LOGITS
     pumped
    0.29
    桶
    0.28
    -tank
    0.26
    rage
    0.23
     водÑĭ
    0.23
    æ°´éĩı
    0.22
    æ³µ
    0.22
     agua
    0.22
    naire
    0.21
    -water
    0.21
    Activations Density 0.006%

    No Known Activations