© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1800
    Prev
    Next
    INDEX
    Explanations

    camera filming recording

    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
    wl
    -0.25
     Jordan
    -0.24
     Virt
    -0.24
    defaults
    -0.24
    osal
    -0.23
    Jordan
    -0.23
    awn
    -0.23
    adel
    -0.23
    éªĦåĤ²
    -0.23
    virt
    -0.22
    POSITIVE LOGITS
    æijĦåĥı
    0.53
     filming
    0.49
    æĭįæijĦ
    0.48
     cameras
    0.47
    æĭįçħ§
    0.47
    è®°å½ķ
    0.46
    æijĦå½±
    0.45
    .capture
    0.45
     camera
    0.44
     recording
    0.43
    Activations Density 0.096%

    No Known Activations