© 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. 9-TRANSCODER-HP
    7. 30017
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    伤çĹħ
    -0.26
    .pad
    -0.25
    SPATH
    -0.24
    æĦ§
    -0.24
    ddit
    -0.24
    ลาà¸Ķ
    -0.24
    ollah
    -0.24
    UTO
    -0.24
    è¥ŀ
    -0.23
    <UFunction
    -0.23
    POSITIVE LOGITS
    è£ħ
    0.27
    pliance
    0.26
    atori
    0.26
    太æ¹ĸ
    0.26
    Alpha
    0.26
    äºĮ次
    0.26
    äºĮæīĭ
    0.25
    etwork
    0.25
    y
    0.25
    å¡ŀ
    0.25
    Activations Density 3.721%

    No Known Activations