© 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. 23-TRANSCODER-HP
    7. 24702
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guide
    -0.28
     mid
    -0.27
    today
    -0.27
     Mid
    -0.27
    ä¿Ŀ
    -0.27
    æĺ¨å¤©
    -0.26
    mid
    -0.26
    tar
    -0.26
    ndx
    -0.26
    ä»Ĭ天
    -0.26
    POSITIVE LOGITS
     życia
    0.28
     getCount
    0.27
     TimeUnit
    0.27
     Sink
    0.26
    edBy
    0.24
    ä¸Ģå¹´å¤ļ
    0.24
     getColumn
    0.24
     Bj
    0.24
    æ²ģ
    0.24
     queried
    0.24
    Activations Density 0.006%

    No Known Activations