© 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. 89063
    Prev
    Next
    INDEX
    Explanations

    CSS

    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
    roud
    -0.29
    ele
    -0.28
    packing
    -0.26
    _ele
    -0.26
    	tab
    -0.25
     replacing
    -0.25
    -pad
    -0.25
    replace
    -0.25
     Tab
    -0.25
    ä¸ļ
    -0.25
    POSITIVE LOGITS
    åħ¨åľº
    0.28
    管å§Ķä¼ļ
    0.26
     Fuse
    0.26
    許
    0.25
     synd
    0.25
    лом
    0.25
    åIJŃ
    0.24
    cases
    0.24
    uki
    0.24
    éĩ
    0.24
    Activations Density 7.145%

    No Known Activations