© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6263
    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
    åħ°èĬ±
    -0.30
     withString
    -0.28
    umbo
    -0.28
    åħ°
    -0.27
    prit
    -0.27
    itech
    -0.26
    ImageContext
    -0.26
    ãĥ§ãĥ³
    -0.25
     unfavor
    -0.25
    amba
    -0.25
    POSITIVE LOGITS
    empt
    0.28
    ì°¨
    0.28
     drip
    0.27
     Drama
    0.27
    FINE
    0.25
    /etc
    0.24
    classpath
    0.24
     unst
    0.24
    >Welcome
    0.24
    throws
    0.24
    Activations Density 0.003%

    No Known Activations