© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58432
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Negative Logits
    .va
    -0.26
    wick
    -0.26
    HEMA
    -0.26
    urities
    -0.26
    Targets
    -0.26
    laces
    -0.26
    æľīä¸Ģä½į
    -0.26
    å°¼äºļ
    -0.26
    对ä¼ģä¸ļ
    -0.25
    abella
    -0.25
    POSITIVE LOGITS
    ogue
    0.26
    满
    0.26
    edin
    0.26
    roit
    0.26
     more
    0.25
     enough
    0.25
     hơn
    0.25
     clamp
    0.24
    滿
    0.24
    &(
    0.23
    Activations Density 0.013%

    No Known Activations