© 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. 39844
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    并åıijçĹĩ
    -0.29
    åĪ¶
    -0.28
    å¾ĩ
    -0.28
    icals
    -0.27
    eler
    -0.27
     gran
    -0.27
    .annotate
    -0.26
     training
    -0.26
    mers
    -0.25
    eller
    -0.25
    POSITIVE LOGITS
    éĤ£æ®µ
    0.28
    鬲
    0.26
    èİŀ
    0.25
    ç®ĢåİĨ
    0.25
     Sus
    0.25
    éĥ
    0.25
    çļĦèĥ½éĩı
    0.24
    OfDay
    0.24
    èµ·çłģ
    0.24
    åī©ä¸ĭçļĦ
    0.24
    Activations Density 2.005%

    No Known Activations