© 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. 88542
    Prev
    Next
    INDEX
    Explanations

    p-values

    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
    tat
    -0.27
    screens
    -0.25
    åħ¹
    -0.25
    æĶ¯çIJĥéĺŁ
    -0.24
    -President
    -0.24
    åħĨ
    -0.24
    æ¸ħæľĿ
    -0.24
     cosmos
    -0.24
    ä¼Ĭ
    -0.23
    rove
    -0.23
    POSITIVE LOGITS
     Boundary
    0.27
    moth
    0.27
     Suddenly
    0.25
     er
    0.25
    acency
    0.25
    è¶ĬæĿ¥è¶Ĭ
    0.25
    aland
    0.24
     suddenly
    0.24
     invisible
    0.24
    æĸŃ
    0.24
    Activations Density 5.240%

    No Known Activations