© 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. 9089
    Prev
    Next
    INDEX
    Explanations

    2

    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
    er
    -0.29
    erate
    -0.27
    nor
    -0.25
    erd
    -0.25
    ash
    -0.25
    ä½ľ
    -0.24
    æĿ¥äºĨ
    -0.24
    rd
    -0.24
    erot
    -0.24
    ROP
    -0.23
    POSITIVE LOGITS
    -thirds
    0.37
    nd
    0.29
    soever
    0.28
    .yahoo
    0.26
    .writeHead
    0.25
    æ·ļ
    0.24
    знаком
    0.24
    forth
    0.24
    .bz
    0.24
    OfFile
    0.23
    Activations Density 1.825%

    No Known Activations