© 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. 89743
    Prev
    Next
    INDEX
    Explanations

    2

    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
     notwithstanding
    -0.28
    åį´è¢«
    -0.28
    (O
    -0.26
    though
    -0.26
    çIJĨäºĭéķ¿
    -0.25
     maiden
    -0.24
    éŀį
    -0.24
    çĦ¶èĢĮ
    -0.24
     nevertheless
    -0.24
     Skip
    -0.24
    POSITIVE LOGITS
    .ModelSerializer
    0.29
    init
    0.27
    ä¸įæĸŃæıIJåįĩ
    0.26
    æīĴ
    0.25
    |array
    0.25
    ewriter
    0.24
     damit
    0.24
    å©ī
    0.24
    OfFile
    0.24
    ä¸¤å¼ł
    0.24
    Activations Density 12.424%

    No Known Activations