© 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. 18-TRANSCODER-HP
    7. 89272
    Prev
    Next
    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĥÑĩ
    -0.29
    qml
    -0.27
     skim
    -0.27
    nap
    -0.25
     voyeur
    -0.25
    -finals
    -0.25
     Em
    -0.25
    edly
    -0.24
    åı¸
    -0.24
    çªĹ
    -0.24
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.29
    è¡Įéķ¿
    0.27
     deps
    0.27
    urus
    0.27
     atol
    0.26
    åĮĹæĸĹ
    0.25
    groupName
    0.25
     roles
    0.25
    roles
    0.24
     allen
    0.24
    Activations Density 3.768%

    No Known Activations