© 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. 40816
    Prev
    Next
    INDEX
    Explanations

    diffusion

    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
    ppers
    -0.29
    elig
    -0.28
    å¿«
    -0.27
    orges
    -0.27
    è¿ĻæĿ¡
    -0.26
    pek
    -0.26
    交代
    -0.25
    iners
    -0.25
    empre
    -0.25
    ¹
    -0.24
    POSITIVE LOGITS
     hopeless
    0.29
     hope
    0.29
     hopes
    0.28
    ç¾Ķ
    0.28
     hoped
    0.24
    .assertRaises
    0.24
     defendant
    0.24
    yon
    0.24
     manip
    0.24
     testimony
    0.23
    Activations Density 0.910%

    No Known Activations