© 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. 19296
    Prev
    Next
    INDEX
    Explanations

    names with "Ray"

    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
     McGregor
    -0.27
    ä¸īåĪĨ
    -0.26
    airo
    -0.25
    ÃĮ
    -0.25
     tü
    -0.25
    ope
    -0.25
    fcn
    -0.24
     Thr
    -0.24
    DEFINE
    -0.24
     Wheel
    -0.24
    POSITIVE LOGITS
    çłĸ
    0.27
    çŃĶåį·
    0.26
     brush
    0.26
    vais
    0.26
     redund
    0.26
    oard
    0.25
    vida
    0.25
    adic
    0.25
     brick
    0.24
    دÙĬØ©
    0.24
    Activations Density 0.393%

    No Known Activations