© 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. 40561
    Prev
    Next
    INDEX
    Explanations

    academic research

    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
    çĤ¹çĤ¹å¤´
    -0.26
    çľĭæĿ¥
    -0.25
    pective
    -0.25
    第äºĮ大
    -0.25
    æĪIJ为ä¸Ģ个
    -0.25
    alk
    -0.25
     Pom
    -0.24
    OffsetTable
    -0.24
     dar
    -0.24
     pom
    -0.23
    POSITIVE LOGITS
    æĦıåij³
    0.27
    åĪĥ
    0.27
    ä¿Ĺ称
    0.27
    REC
    0.27
    èī°
    0.26
     abbreviation
    0.25
    ç®Ģ称
    0.25
     (:
    0.25
     ([[
    0.25
     (“
    0.25
    Activations Density 2.525%

    No Known Activations