© 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. 12-TRANSCODER-HP
    7. 22564
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Compatible
    -0.28
     kaç
    -0.27
    å®
    -0.26
    opal
    -0.25
    UIT
    -0.24
    .Are
    -0.24
     Yii
    -0.24
    æ°ª
    -0.24
    ushima
    -0.23
     distinct
    -0.23
    POSITIVE LOGITS
    æīĵäºĨ
    0.28
    éĶij
    0.26
    æīĵ好
    0.26
    è¿ĺ没æľī
    0.26
    annah
    0.25
    éĥ¨
    0.25
    annya
    0.25
    ä½ľäºĨ
    0.25
    æĬĦ
    0.25
    è¨Ĭ
    0.24
    Activations Density 0.000%

    No Known Activations