© 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. 41351
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    stantiate
    -0.30
    otted
    -0.26
    otts
    -0.26
    arus
    -0.26
     unloaded
    -0.25
     disclaimer
    -0.25
     EVT
    -0.24
    asonry
    -0.24
     usur
    -0.24
    æķ¢
    -0.24
    POSITIVE LOGITS
    æĺ¾
    0.27
    ç»ī
    0.26
    ä¹ĭ家
    0.26
    第ä¸ĢæĿ¡
    0.25
    æĿijéĩĮ
    0.25
    éªļ
    0.24
    -se
    0.24
    çıŃ级
    0.24
    å¢ŀéķ¿çİĩ
    0.24
    类产åĵģ
    0.24
    Activations Density 1.289%

    No Known Activations