© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    èĪį
    -0.27
     fac
    -0.25
     Setup
    -0.24
     round
    -0.24
    ʲ
    -0.24
     getNode
    -0.23
     pref
    -0.23
    shares
    -0.23
    Setup
    -0.23
     playa
    -0.23
    POSITIVE LOGITS
    ON
    0.28
    &P
    0.27
    .management
    0.27
    _DC
    0.26
    é£Ļ
    0.25
    он
    0.25
    berman
    0.24
    è´¢åĬ¡ç®¡çIJĨ
    0.23
     understandable
    0.23
    DH
    0.23
    Activations Density 0.010%

    No Known Activations