© 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. 40848
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ç¢ĩ
    -0.27
    èĩªçĦ¶
    -0.26
    uale
    -0.26
    ivities
    -0.26
    aped
    -0.26
    getti
    -0.26
     giáo
    -0.25
    ione
    -0.25
    uais
    -0.25
     Thảo
    -0.25
    POSITIVE LOGITS
    @Web
    0.26
    为ä»Ģä¹Īä¸į
    0.25
    WithTag
    0.25
     pretext
    0.25
     suggestion
    0.25
     corrobor
    0.25
     jr
    0.24
    æ»ĭçĶŁ
    0.24
    è¦ģ害
    0.24
    æĹłéļľç¢į
    0.24
    Activations Density 0.099%

    No Known Activations