© 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. 40464
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ziaÅĤ
    -0.26
    abeth
    -0.26
    ]int
    -0.25
     ÑĥÑģлов
    -0.25
    atrix
    -0.25
     Intersection
    -0.25
    è·¯
    -0.25
    asser
    -0.24
    Ĭ¶
    -0.24
    ctic
    -0.23
    POSITIVE LOGITS
    åį´è¢«
    0.29
    ElapsedTime
    0.26
    è¿Ļæľ¬ä¹¦
    0.25
    idel
    0.25
    pson
    0.25
    æű
    0.25
    -work
    0.25
    etwork
    0.25
    æľ¬æĽ¸
    0.24
    çļĦ对象
    0.23
    Activations Density 0.179%

    No Known Activations