© 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. 695
    Prev
    Next
    INDEX
    Explanations

    organizational units and locations

    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
    æį®
    -0.25
    encers
    -0.24
    ammo
    -0.24
    eo
    -0.23
    Chunks
    -0.22
    æĭ©
    -0.22
    çĪ±æĬ¤
    -0.22
     Millions
    -0.21
     medically
    -0.21
    éĺĶ
    -0.21
    POSITIVE LOGITS
    lain
    0.30
    åIJį称
    0.27
    .department
    0.27
    layan
    0.26
     affiliation
    0.26
     Institution
    0.25
     departments
    0.25
    æľºæŀĦ
    0.24
     Gow
    0.23
     affili
    0.23
    Activations Density 0.067%

    No Known Activations