© 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. 19514
    Prev
    Next
    INDEX
    Explanations

    Middle

    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
    aldi
    -0.30
     cold
    -0.29
     modern
    -0.28
    .comm
    -0.27
    WithContext
    -0.26
     pan
    -0.26
    autos
    -0.25
    acco
    -0.25
     inf
    -0.25
    Cold
    -0.24
    POSITIVE LOGITS
    emes
    0.28
     tek
    0.28
    LETE
    0.27
    reeting
    0.26
    uters
    0.26
     Interrupt
    0.26
    irting
    0.25
    BED
    0.25
     BaseEntity
    0.24
    ä»ĭè´¨
    0.24
    Activations Density 0.977%

    No Known Activations