© 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. 31-TRANSCODER-HP
    7. 19455
    Prev
    Next
    INDEX
    Explanations

    technology-related description

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cons
    -0.66
    cons
    -0.62
     cons
    -0.60
    Cons
    -0.60
    -cons
    -0.52
    .cons
    -0.50
     CONS
    -0.46
    CONS
    -0.44
     consistency
    -0.44
    _cons
    -0.44
    POSITIVE LOGITS
    åĮħæĭ¬
    1.23
     including
    1.20
     Including
    1.09
     include
    1.08
    including
    1.07
     includes
    0.98
    include
    0.96
    Including
    0.95
    è¿ĺåĮħæĭ¬
    0.93
    Include
    0.91
    Activations Density 6.342%

    No Known Activations