© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8817
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aat
    -0.28
     declares
    -0.27
    ician
    -0.26
    æĮĤéĴ©
    -0.26
    äter
    -0.26
     dedicate
    -0.25
    级
    -0.25
    داÙĨ
    -0.25
     spe
    -0.25
     declare
    -0.25
    POSITIVE LOGITS
    æĢ»æĶ¶åħ¥
    0.26
    é¦ĸå¯Į
    0.25
    è¶ħé¢Ŀ
    0.25
    (Default
    0.25
    Regression
    0.24
    æľĢåIJİä¸Ģ次
    0.24
    èĥľè´Ł
    0.24
    ensus
    0.24
     adjusted
    0.24
     increasingly
    0.23
    Activations Density 0.005%

    No Known Activations