© 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. 40927
    Prev
    Next
    INDEX
    Explanations

    back

    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
    ucht
    -0.26
     kapsam
    -0.26
     kaps
    -0.26
    trak
    -0.25
    cps
    -0.25
    overflow
    -0.24
    æݬ
    -0.24
    wick
    -0.24
     Coke
    -0.24
    handled
    -0.24
    POSITIVE LOGITS
    éŀij
    0.28
    ä¸ĢéĿ¢
    0.25
    .hot
    0.25
    .erb
    0.24
    çĽ¾
    0.24
    çıŃ
    0.24
    oton
    0.24
    éĥ½å¸Ĥ
    0.24
    angelog
    0.24
     oppon
    0.23
    Activations Density 2.529%

    No Known Activations