© 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. 615
    Prev
    Next
    INDEX
    Explanations

    chalk + boardchiff

    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
    igid
    -0.20
    uality
    -0.20
    ntag
    -0.20
     einzel
    -0.19
     Uh
    -0.19
     Sons
    -0.19
    é©·
    -0.19
    çľĩ
    -0.18
     Clip
    -0.18
    nty
    -0.18
    POSITIVE LOGITS
    board
    0.28
    boards
    0.27
    mates
    0.24
    boarding
    0.24
    town
    0.23
    leton
    0.23
    stone
    0.23
    busters
    0.22
    stones
    0.22
    hurst
    0.22
    Activations Density 0.004%

    No Known Activations