© 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. 8750
    Prev
    Next
    INDEX
    Explanations

    in/into

    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
    ioned
    -0.32
    ationally
    -0.27
    wers
    -0.27
    ноп
    -0.26
    åįĸæİī
    -0.26
    <Form
    -0.25
    Delayed
    -0.24
    gli
    -0.24
    =form
    -0.24
    /form
    -0.24
    POSITIVE LOGITS
     strips
    0.28
    дÑĥмал
    0.28
     pieces
    0.27
     triple
    0.26
     Edison
    0.26
     vir
    0.25
     ninth
    0.25
    迹
    0.25
    缸è§ģ
    0.25
     lava
    0.24
    Activations Density 0.001%

    No Known Activations