© 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. 2486
    Prev
    Next
    INDEX
    Explanations

    Wal followed by words

    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
    ãģĦãĤĭ
    -0.24
    ReturnValue
    -0.21
    ãĤĤãģ®
    -0.20
    lw
    -0.19
    PerPixel
    -0.19
    ning
    -0.18
    lish
    -0.18
    IVES
    -0.18
    ãĤ§
    -0.18
    lander
    -0.18
    POSITIVE LOGITS
    yard
    0.26
    bone
    0.25
    大å¦Ī
    0.20
    bury
    0.20
    ston
    0.19
    -scale
    0.19
    grave
    0.18
    wards
    0.18
    Å¡ÃŃ
    0.18
    hips
    0.17
    Activations Density 0.017%

    No Known Activations