© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tribution
    -0.30
    åijĬ
    -0.26
    å¾Īæľī
    -0.25
    ãĤ¯ãĥ©ãĥĸ
    -0.24
    çĴŀ
    -0.24
    jango
    -0.23
    implode
    -0.23
    luet
    -0.23
    ucht
    -0.23
    han
    -0.23
    POSITIVE LOGITS
    è¹Ń
    0.27
    доÑĢ
    0.27
    å¢ĥ
    0.26
    ROY
    0.26
    -present
    0.26
    ÙħÙĪا
    0.25
    chy
    0.25
    (""+
    0.25
    颦
    0.24
    -Co
    0.24
    Activations Density 0.024%

    No Known Activations