© 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. 41077
    Prev
    Next
    INDEX
    Explanations

    week

    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
    为ä¸Ńå¿ĥ
    -0.32
     uncomment
    -0.27
    nih
    -0.25
    çīĪæĿĥæīĢæľī
    -0.25
    _payments
    -0.25
    (Controller
    -0.25
    -hooks
    -0.25
    å¹ķ
    -0.24
    ajs
    -0.24
     Collider
    -0.24
    POSITIVE LOGITS
    ä¾Ĩèĩª
    0.27
    åłij
    0.26
    ITCH
    0.26
    è¿Ļ个åIJįåŃĹ
    0.25
     ace
    0.24
    åѦåijĺ
    0.24
    çĦ¶
    0.24
    çĶ¨æĪ·ä½ĵéªĮ
    0.24
     Marg
    0.24
     ìłģ
    0.24
    Activations Density 0.358%

    No Known Activations