© 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. 762
    Prev
    Next
    INDEX
    Explanations

    group activities and discussions

    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
    gfx
    -0.24
    alles
    -0.24
    以éĺ²
    -0.24
     cabinets
    -0.22
     appar
    -0.22
    ocks
    -0.21
    ander
    -0.21
     Metallic
    -0.21
     supern
    -0.21
     Origin
    -0.20
    POSITIVE LOGITS
    åħ±äº«
    0.47
     shared
    0.46
    åħ±åIJĮ
    0.44
    大家ä¸Ģèµ·
    0.43
    shared
    0.43
    讨论
    0.42
     Shared
    0.40
    ä¸Ģèµ·
    0.40
    (shared
    0.40
     discussion
    0.39
    Activations Density 0.116%

    No Known Activations