© 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. 41095
    Prev
    Next
    INDEX
    Explanations

    Technical topics

    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
    åľ°æ®µ
    -0.27
    åĺ¿åĺ¿
    -0.26
     KeyError
    -0.26
    _Native
    -0.25
     compartments
    -0.25
    é«Ģ
    -0.25
    è¾ĩ
    -0.24
     Silence
    -0.24
     Kern
    -0.24
    Kernel
    -0.24
    POSITIVE LOGITS
    óa
    0.29
     downt
    0.28
    åīįçŀ»
    0.28
    etty
    0.27
    æµĶ
    0.26
    edicine
    0.25
    rones
    0.25
     indefinite
    0.25
    æĪª
    0.25
     propTypes
    0.24
    Activations Density 0.921%

    No Known Activations