© 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. 27-TRANSCODER-HP
    7. 9434
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edImage
    -0.26
     Ku
    -0.26
    stown
    -0.26
    dess
    -0.25
    lua
    -0.25
    ovsky
    -0.25
    Lua
    -0.25
    qli
    -0.24
    ugging
    -0.24
     sürü
    -0.24
    POSITIVE LOGITS
    çŁ
    0.25
    ESIS
    0.25
    rina
    0.24
     behalf
    0.24
    âĢ
    0.24
    otics
    0.24
    esis
    0.24
    综åIJĪæķ´æ²»
    0.23
     opposite
    0.23
    ä¼ļéĢłæĪIJ
    0.23
    Activations Density 0.000%

    No Known Activations