© 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. 40660
    Prev
    Next
    INDEX
    Explanations

    rockets and flight

    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
    ä¸į说
    -0.26
    otomy
    -0.25
    .Gravity
    -0.25
     paper
    -0.24
    ationToken
    -0.24
    æł¹åŁº
    -0.24
    obl
    -0.24
    ocols
    -0.24
    ä¸Ģèīĺ
    -0.23
     |--
    -0.23
    POSITIVE LOGITS
    eno
    0.29
     Arc
    0.27
     Arb
    0.26
    urus
    0.25
    isable
    0.25
     assignable
    0.24
    DSL
    0.24
    èģĮèĥ½
    0.23
     innoc
    0.23
     crisp
    0.23
    Activations Density 0.303%

    No Known Activations