© 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. 40750
    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
    uters
    -0.31
    èģŀãģı
    -0.26
    åĩ¡æĺ¯
    -0.25
    astically
    -0.25
    /fast
    -0.25
    ulary
    -0.24
     occ
    -0.24
    quals
    -0.24
    care
    -0.24
    blast
    -0.24
    POSITIVE LOGITS
    åĽłåľ°åĪ¶å®ľ
    0.27
    æĮĩåIJij
    0.27
    俱ä¹IJéĥ¨
    0.26
    бе
    0.25
    gether
    0.24
    olley
    0.23
    ken
    0.23
    .urls
    0.23
    æľªç»ıæİĪæĿĥ
    0.23
     Club
    0.23
    Activations Density 1.370%

    No Known Activations