© 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. 40049
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    ofi
    -0.27
    éľľ
    -0.27
    .hasMore
    -0.25
    ża
    -0.25
     progressive
    -0.25
     defs
    -0.25
    wayne
    -0.24
    RIX
    -0.24
    å½¢æĪIJ
    -0.24
    è¹Ħ
    -0.24
    POSITIVE LOGITS
    orting
    0.27
    æľī幸
    0.26
     chaining
    0.25
    Reverse
    0.24
    úng
    0.24
     Preconditions
    0.24
    ä¸Ģäºĭ
    0.24
    rangle
    0.24
    è¿ĩåIJİ
    0.24
    Messenger
    0.24
    Activations Density 1.287%

    No Known Activations