© 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. 40092
    Prev
    Next
    INDEX
    Explanations

    period

    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
    馨
    -0.29
    itto
    -0.26
     honour
    -0.26
    resse
    -0.26
    Dup
    -0.25
    anager
    -0.25
    ounc
    -0.25
    oulouse
    -0.24
    ä¹Łæĺ¯ä¸Ģ个
    -0.24
    anka
    -0.24
    POSITIVE LOGITS
     Pot
    0.28
    第ä¸Ģéĥ¨
    0.27
    Pot
    0.26
    æµģ浪
    0.26
    chu
    0.25
    Everything
    0.24
    è°¢
    0.24
    æ·ĺ
    0.24
    欢è¿İæĤ¨
    0.23
    åijĪçİ°åĩº
    0.23
    Activations Density 0.224%

    No Known Activations