© 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. 18-TRANSCODER-HP
    7. 88786
    Prev
    Next
    INDEX
    Explanations

    Code and terminal output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dip
    -0.28
     Degree
    -0.28
    度
    -0.27
    ring
    -0.27
    ucer
    -0.26
    -Day
    -0.25
    ä¸ĢæľŁ
    -0.25
    -Mobile
    -0.24
    éĹ¼
    -0.24
    ala
    -0.24
    POSITIVE LOGITS
    æĪij以为
    0.27
    anship
    0.26
     mish
    0.26
    Bow
    0.26
    èµ¢å¾Ĺ
    0.25
     Tourism
    0.25
    è¯ķ管婴åĦ¿
    0.25
    _:
    0.24
    åĻ±
    0.23
     quot
    0.23
    Activations Density 1.917%

    No Known Activations