© 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. 20-TRANSCODER-HP
    7. 142312
    Prev
    Next
    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILON
    -0.29
    lando
    -0.27
    otion
    -0.26
    纵深
    -0.25
    sport
    -0.25
    alter
    -0.25
    å¹»
    -0.25
    (bot
    -0.24
    alue
    -0.24
    usi
    -0.24
    POSITIVE LOGITS
    ç°ĭ
    0.27
    .basicConfig
    0.25
     paras
    0.25
    EO
    0.25
    è¦ģåıĬæŶ
    0.24
     slips
    0.24
    æĢ§å¼º
    0.23
    ÑĥÑĩа
    0.23
    -filled
    0.23
    º«
    0.23
    Activations Density 8.316%

    No Known Activations