© 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. 39914
    Prev
    Next
    INDEX
    Explanations

    transcript

    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
    ipi
    -0.29
    istant
    -0.27
    ×ļ
    -0.25
    æĥ³èµ·
    -0.25
    ayout
    -0.24
    zap
    -0.24
    åĮĸ
    -0.24
    åĩĨ
    -0.23
    Paginator
    -0.23
     maka
    -0.23
    POSITIVE LOGITS
    äºĨä¸ĭæĿ¥
    0.27
    æĪIJé¾Ļ
    0.27
    ä¸ī项
    0.26
    ERO
    0.25
    dney
    0.25
    两项
    0.25
    plorer
    0.24
    lix
    0.24
    æĶ¾å¼ĥäºĨ
    0.24
    trail
    0.24
    Activations Density 0.440%

    No Known Activations