© 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. 41271
    Prev
    Next
    INDEX
    Explanations

    Data snippets

    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
     compliance
    -0.28
    ney
    -0.26
     typings
    -0.25
    _callbacks
    -0.25
    jam
    -0.25
    è¾ĥä½İ
    -0.25
    tank
    -0.24
    åĬ¨æijĩ
    -0.24
     slashing
    -0.24
    女
    -0.24
    POSITIVE LOGITS
    IC
    0.29
     poc
    0.27
     Laz
    0.25
    ä¸įä½ı
    0.25
     sacrifice
    0.25
    æĦıæĦ¿
    0.24
    episode
    0.24
    åijĭ
    0.24
    PD
    0.24
    PC
    0.23
    Activations Density 0.911%

    No Known Activations