© 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. 8261
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ®ĥ
    -0.27
    ipers
    -0.26
    bes
    -0.25
    бÑĢи
    -0.25
    款车åŀĭ
    -0.25
    åı¸
    -0.25
    ordan
    -0.24
    款
    -0.24
    å¯Ĩ
    -0.24
    å¡Ķ
    -0.24
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.33
     further
    0.28
    éĢ²ä¸ĢæŃ¥
    0.28
     retailer
    0.27
     occasion
    0.26
    onium
    0.26
    æĪIJåĬŁ
    0.25
     turning
    0.25
    icted
    0.25
    æĿĵ
    0.24
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.