© 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. 40793
    Prev
    Next
    INDEX
    Explanations

    sounds

    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
    -US
    -0.28
    çłŃ
    -0.27
     upsetting
    -0.25
    æĦıå¤ĸ
    -0.24
    на
    -0.24
    çĪ·
    -0.24
     alternate
    -0.24
     unint
    -0.23
    å¨ĥ
    -0.23
     Stock
    -0.23
    POSITIVE LOGITS
    andum
    0.31
    OLA
    0.27
    åĪĽæĸ°èĥ½åĬĽ
    0.26
    cretion
    0.26
     mcc
    0.25
    uent
    0.25
    otate
    0.24
    atty
    0.24
    .CreateTable
    0.24
    past
    0.24
    Activations Density 0.077%

    No Known Activations