© 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. 18-TRANSCODER-HP
    7. 89508
    Prev
    Next
    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.30
     squash
    -0.25
    è¯ģ书
    -0.24
    溶
    -0.24
    åĩºäº§
    -0.24
    沪深
    -0.24
    产çī©
    -0.24
    åħļçļĦ
    -0.23
    QRST
    -0.23
    AsStream
    -0.23
    POSITIVE LOGITS
    人åĿĩ
    0.33
    agements
    0.30
    ä¸Ģ举
    0.29
    ä¸Ģç¬Ķ
    0.27
     cabe
    0.27
    课åłĤ
    0.27
    achment
    0.26
    å¸ĥå±Ģ
    0.25
    avigation
    0.24
     HOLD
    0.24
    Activations Density 27.451%

    No Known Activations