© 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. 40796
    Prev
    Next
    INDEX
    Explanations

    Code and reverse engineering

    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
    èĤĮèĤ¤
    -0.30
    ä¹±
    -0.28
    æĥľ
    -0.28
     Odd
    -0.28
     Abb
    -0.28
    çĹĪ
    -0.27
     rocky
    -0.26
    contre
    -0.26
    å¥ĩ
    -0.26
    USH
    -0.26
    POSITIVE LOGITS
    _PRESENT
    0.27
    .masks
    0.26
    ansk
    0.26
    å¼¼
    0.25
    .Visibility
    0.25
    jin
    0.25
    /cal
    0.25
    æĶ¾è¿ĩ
    0.24
    íĽĦ
    0.24
    Trail
    0.24
    Activations Density 0.272%

    No Known Activations