© 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. 18-TRANSCODER-HP
    7. 89147
    Prev
    Next
    INDEX
    Explanations

    scientific studies/journals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tog
    -0.30
     tore
    -0.27
    éĢļ常æĺ¯
    -0.27
     plead
    -0.27
    ç½Ħ
    -0.26
     REUTERS
    -0.26
    ",__
    -0.26
    )();↵
    -0.24
    åĴ¿
    -0.24
    .localized
    -0.24
    POSITIVE LOGITS
     Reporting
    0.26
    unde
    0.25
    Reporting
    0.25
    cker
    0.25
    ion
    0.25
    åģļ个
    0.24
     reporting
    0.24
     Fine
    0.24
    leck
    0.24
    è°ĥçłĶ
    0.24
    Activations Density 3.615%

    No Known Activations