© 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. 31-TRANSCODER-HP
    7. 19550
    Prev
    Next
    INDEX
    Explanations

    Source code/licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    light
    -0.26
    laps
    -0.26
     ecl
    -0.26
    ulary
    -0.25
    åįģäºĮ
    -0.25
     /*----------------------------------------------------------------
    -0.25
    身
    -0.24
    æ»ĭ
    -0.24
    åħī线
    -0.24
     Light
    -0.24
    POSITIVE LOGITS
    STORE
    0.27
     acids
    0.27
     Store
    0.25
    åħĢ
    0.25
    acf
    0.25
    æĽ²çº¿
    0.24
    loth
    0.24
    iona
    0.23
    款å¼ı
    0.23
    aurus
    0.23
    Activations Density 0.002%

    No Known Activations