© 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. 41107
    Prev
    Next
    INDEX
    Explanations

    computer code, posts

    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
    çĤŃ
    -0.27
    :checked
    -0.26
    ,eg
    -0.25
    =count
    -0.25
    loom
    -0.25
    accessible
    -0.25
    [count
    -0.25
    [random
    -0.25
    èħ¹
    -0.25
    som
    -0.24
    POSITIVE LOGITS
    ENTE
    0.29
    ç¼´è´¹
    0.27
    apist
    0.26
    çIJĨ解
    0.26
    /tty
    0.25
    èµ·
    0.25
    stell
    0.24
    ä¸Ģè´¯
    0.24
    æĪ¿
    0.24
    延éķ¿
    0.24
    Activations Density 2.189%

    No Known Activations