© 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. 18570
    Prev
    Next
    INDEX
    Explanations

    software code

    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
    аÑĢам
    -0.31
    CONS
    -0.26
    iera
    -0.25
    (chart
    -0.25
    éŁŃ
    -0.25
     Dom
    -0.24
    Dom
    -0.24
     Harry
    -0.24
    PEC
    -0.24
    ám
    -0.24
    POSITIVE LOGITS
    icia
    0.27
    Match
    0.26
    æij©æĵ¦
    0.26
    æķĸ
    0.24
    leftrightarrow
    0.24
    match
    0.24
    elif
    0.24
    ople
    0.24
    lock
    0.24
    cher
    0.23
    Activations Density 0.327%

    No Known Activations