© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    titles or solar

    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
    ä¸Ģ件
    -0.28
    ä¸ĢåIJį
    -0.27
     Developing
    -0.27
    è¯ŀ
    -0.26
    bie
    -0.26
    osg
    -0.24
    踵
    -0.24
    UX
    -0.24
     ratio
    -0.24
     développe
    -0.24
    POSITIVE LOGITS
     clouds
    0.28
    fur
    0.27
     "(\<
    0.26
     squ
    0.26
    led
    0.25
    /cloud
    0.25
    entina
    0.25
    临
    0.25
     storms
    0.25
     operations
    0.25
    Activations Density 0.001%

    No Known Activations