© 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. 8621
    Prev
    Next
    INDEX
    Explanations

    Institutions

    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
    agnostic
    -0.30
    {text
    -0.27
    à¤ĸ
    -0.26
    ngth
    -0.26
    agonal
    -0.25
    _aligned
    -0.25
    .configuration
    -0.25
    thern
    -0.24
    åıĹçĽĬ
    -0.24
    æŃ£å¼ıåIJ¯åĬ¨
    -0.24
    POSITIVE LOGITS
     sitio
    0.26
    ea
    0.26
    romise
    0.26
    .dt
    0.25
     efforts
    0.25
    ORG
    0.25
    VERIFY
    0.25
    eff
    0.25
     dt
    0.24
    uby
    0.24
    Activations Density 0.034%

    No Known Activations