© 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. 130272
    Prev
    Next
    INDEX
    Explanations

    type/kind

    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
     PGA
    -0.27
    _IE
    -0.27
     ECB
    -0.25
    .getOwnProperty
    -0.24
     shalt
    -0.24
    üzü
    -0.23
    ecret
    -0.23
    ä¸ĩä¸Ģ
    -0.23
    å§Ķ
    -0.23
    ç±į
    -0.23
    POSITIVE LOGITS
    票
    0.27
     scale
    0.26
    бÑĢа
    0.25
     FAR
    0.25
     scales
    0.25
    á¸į
    0.24
    åĦ¿
    0.24
    Br
    0.24
    -l
    0.24
    GRA
    0.24
    Activations Density 14.971%

    No Known Activations