© 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. 130228
    Prev
    Next
    INDEX
    Explanations

    scientific/academic text

    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
    apore
    -0.25
    è¿Ļå°±æĺ¯
    -0.25
    [offset
    -0.25
    olem
    -0.25
     replacing
    -0.24
    Dir
    -0.24
    iem
    -0.24
     Dia
    -0.24
    _aff
    -0.24
    ç¹ģå¿Ļ
    -0.24
    POSITIVE LOGITS
    esting
    0.28
    å¼
    0.27
    çļĦç»ĵæŀľ
    0.26
    ç¢İçīĩ
    0.26
    她们
    0.26
    ä¸Ĭ游
    0.25
    çļĦåıijçĶŁ
    0.25
    亿åħĥ以ä¸Ĭ
    0.25
    serialized
    0.25
     bear
    0.24
    Activations Density 38.029%

    No Known Activations