© 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. 20-TRANSCODER-HP
    7. 107765
    Prev
    Next
    INDEX
    Explanations

    Prepositions and numerical values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prep
    -0.27
    /register
    -0.27
    Ĭ¶
    -0.26
     subscription
    -0.26
    å¤ĩæĪĺ
    -0.26
    NCY
    -0.25
    odon
    -0.25
    vak
    -0.25
    registration
    -0.25
    ä¸ĬçıŃæĹı
    -0.24
    POSITIVE LOGITS
    æĤ¬å¿µ
    0.27
    !!.
    0.26
    çļĦåĮºåĪ«
    0.26
    éĩĮ
    0.25
    ))==
    0.25
    ieÅĦ
    0.25
    ore
    0.24
    ön
    0.24
    -li
    0.24
    Liv
    0.24
    Activations Density 15.438%

    No Known Activations