© 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. 39943
    Prev
    Next
    INDEX
    Explanations

    playing videos or music

    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
    è¡¥åģ¿
    -0.28
    ع
    -0.27
    æī¿
    -0.26
    åıij
    -0.26
    æĬ¥åºŁ
    -0.25
    _PACK
    -0.23
    .circular
    -0.23
    бол
    -0.23
     za
    -0.23
    za
    -0.23
    POSITIVE LOGITS
    æĬĬæīĭ
    0.34
    æĬĬä»ĸ
    0.30
    tro
    0.28
     rusty
    0.27
     legs
    0.27
    çī¹ç§į
    0.26
    èħ¿
    0.26
    å¿ĹæĦ¿
    0.25
    mel
    0.25
    -leg
    0.25
    Activations Density 1.131%

    No Known Activations