© 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. 14-TRANSCODER-HP
    7. 41109
    Prev
    Next
    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĤ¹åĩ»æŁ¥çľĭ
    -0.02
    ppo
    -0.01
    åħħå®ŀ
    -0.01
    ç¿Ĵ
    -0.01
     Records
    -0.01
    æī©å»º
    -0.01
    æīĭæİĮ
    -0.01
    åIJ¸æĶ¶
    -0.01
    åłĤ
    -0.01
    ä¹ĭ称
    -0.01
    POSITIVE LOGITS
    说æĺİ
    0.01
    è¿Ļä¹Īå¤ļ
    0.01
    å´´
    0.01
    ä¸Ģ个èģĮä¸ļ
    0.01
    itles
    0.01
    _BR
    0.01
    -medium
    0.01
     followed
    0.01
    lessly
    0.01
    .hasMore
    0.01
    Activations Density 3.056%

    No Known Activations