© 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. 40678
    Prev
    Next
    INDEX
    Explanations

    Location, names, legal references

    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
    è¿Ľåİ»
    -0.26
     orally
    -0.25
    èı
    -0.25
    åIJ¬è¿ĩ
    -0.25
    TURN
    -0.24
     toán
    -0.23
     laying
    -0.23
    è¿ijå¹´
    -0.23
    ritten
    -0.23
     Recent
    -0.23
    POSITIVE LOGITS
    寥
    0.30
    æĸ°éĹ»ç½ij
    0.28
    ervo
    0.27
    éĴĪ
    0.27
    rame
    0.26
     Limited
    0.25
    æºħ
    0.25
    çŃĶåį·
    0.24
    æĪŁ
    0.24
    æ·±åĮĸæĶ¹éĿ©
    0.24
    Activations Density 0.048%

    No Known Activations