© 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. 14-TRANSCODER-HP
    7. 40351
    Prev
    Next
    INDEX
    Explanations

    Barbara

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oz
    -0.28
     math
    -0.27
    å¿ħä¸įåı¯
    -0.26
     TODAY
    -0.26
    arena
    -0.26
    replace
    -0.25
     oz
    -0.24
     replacement
    -0.24
     Factory
    -0.24
    usable
    -0.24
    POSITIVE LOGITS
    RIC
    0.26
    .Mode
    0.26
    é¹Ĺ
    0.26
    иÑħ
    0.25
     normals
    0.24
    owe
    0.24
    ató
    0.24
    ÑĦон
    0.24
     Kw
    0.24
    CHASE
    0.24
    Activations Density 1.418%

    No Known Activations