© 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. 39887
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĸ»
    -0.28
    ulas
    -0.27
    izi
    -0.26
    etry
    -0.25
    åIJĦèĩªçļĦ
    -0.24
    iley
    -0.24
     courses
    -0.23
    åIJĦèĩª
    -0.23
    har
    -0.23
    èĨ³
    -0.23
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.29
    å¢ŀéĩı
    0.28
     gren
    0.27
     Tall
    0.26
    Incre
    0.26
    å¥ĩ
    0.25
     =",
    0.25
    å¯Ĩ度
    0.24
    .gf
    0.24
    chet
    0.24
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.