© 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. 88922
    Prev
    Next
    INDEX
    Explanations

    background information

    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
    rese
    -0.32
    æľīæĦıæĢĿçļĦ
    -0.31
     insight
    -0.30
    è§ģ解
    -0.30
    è¶ĭåĬ¿
    -0.29
     interesting
    -0.29
     trends
    -0.28
     trend
    -0.27
    æľīæĦıæĢĿ
    -0.27
    interesting
    -0.27
    POSITIVE LOGITS
    IGNORE
    0.34
    ignore
    0.29
    é¦ĸ
    0.28
     Ignore
    0.28
    utoff
    0.26
    躯
    0.26
     dever
    0.26
    iculo
    0.25
    igit
    0.25
    .ignore
    0.25
    Activations Density 40.346%

    No Known Activations