© 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. 9056
    Prev
    Next
    INDEX
    Explanations

    code snippets and lists

    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
    rien
    -0.28
     EI
    -0.26
     selectedIndex
    -0.25
    selectedIndex
    -0.24
    Twig
    -0.24
    endpoint
    -0.24
     whichever
    -0.24
     FileAccess
    -0.24
    shaw
    -0.23
    /*----------------------------------------------------------------
    -0.23
    POSITIVE LOGITS
     nhắc
    0.28
     Ital
    0.28
    _DP
    0.27
    inus
    0.26
    addTo
    0.26
    dto
    0.26
    [NUM
    0.26
    ICAL
    0.25
    arlo
    0.25
    Italy
    0.25
    Activations Density 0.068%

    No Known Activations