© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 308
    Prev
    Next
    INDEX
    Explanations

    deposition or formation

    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
     publishing
    -0.27
    -setup
    -0.24
     hạng
    -0.23
     Broadcasting
    -0.23
    人éĢī
    -0.23
     bầu
    -0.23
     Shake
    -0.23
     publisher
    -0.23
    çģµæ´»æĢ§
    -0.23
     setup
    -0.23
    POSITIVE LOGITS
     formation
    0.50
    积累
    0.48
     accumulation
    0.47
     Formation
    0.46
     deposits
    0.46
    Formation
    0.44
    æ²ī积
    0.44
    å½¢æĪIJçļĦ
    0.43
     formations
    0.43
     formed
    0.42
    Activations Density 0.283%

    No Known Activations