© 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. 57602
    Prev
    Next
    INDEX
    Explanations

    words with "ir/re/res-" prefix

    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
    ahead
    -0.28
     Maid
    -0.27
    epam
    -0.27
    gee
    -0.27
     cams
    -0.26
    mint
    -0.26
     plaisir
    -0.26
    ardy
    -0.25
    bnb
    -0.25
    elist
    -0.25
    POSITIVE LOGITS
    å¥Ħ
    0.33
    ational
    0.28
     functional
    0.26
    pot
    0.26
     bracket
    0.26
    posed
    0.24
     Functional
    0.24
    åĬŁèĥ½æĢ§
    0.24
    oc
    0.24
    aturity
    0.24
    Activations Density 0.003%

    No Known Activations