© 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. 12-TRANSCODER-HP
    7. 22877
    Prev
    Next
    INDEX
    Explanations

    hours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ино
    -0.27
    _refer
    -0.25
    agger
    -0.24
     clinging
    -0.24
     tam
    -0.24
    صاد
    -0.24
    cı
    -0.24
     réfé
    -0.24
    æķijæĬ¤
    -0.24
    转载请
    -0.23
    POSITIVE LOGITS
    éŃĶ鬼
    0.31
    âĹ»
    0.28
    series
    0.27
     wit
    0.27
    mith
    0.26
    pow
    0.26
    èħ¥
    0.25
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.25
    -flex
    0.25
    dit
    0.24
    Activations Density 0.000%

    No Known Activations