© 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. 19-TRANSCODER-HP
    7. 8445
    Prev
    Next
    INDEX
    Explanations

    places and their history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ci
    -0.30
    åĪ°çİ°åľ¨
    -0.27
    ild
    -0.26
    æ·Ģ
    -0.25
    icle
    -0.24
    èµĦæºIJæķ´åIJĪ
    -0.24
    ä¸įä¹ħ
    -0.24
    åĪģ
    -0.24
    +-+-
    -0.24
    cil
    -0.24
    POSITIVE LOGITS
    éĩĩ
    0.28
    åijĬ
    0.28
    _suite
    0.26
    åħ¥
    0.26
    åĽĽæĸ¹
    0.26
     Contracts
    0.25
     thought
    0.25
    èµ°åİ»
    0.25
    IRM
    0.25
    çļĩ
    0.24
    Activations Density 0.008%

    No Known Activations