© 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. 23-TRANSCODER-HP
    7. 24938
    Prev
    Next
    INDEX
    Explanations

    Media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľå®¶
    -0.49
    åĪĽä½ľ
    -0.43
     writer
    -0.43
    é¢ĺæĿIJ
    -0.41
    ä½ľèĢħ
    -0.41
    å°ı说
    -0.40
    æķ£æĸĩ
    -0.40
    ä½ľåĵģ
    -0.39
    çļĦä½ľåĵģ
    -0.39
     poem
    -0.39
    POSITIVE LOGITS
    Testing
    0.27
    testing
    0.26
    pect
    0.24
     reps
    0.24
     Testing
    0.24
    åĩºå¸Ńä¼ļè®®
    0.23
    èij¡èIJĦ
    0.23
    Thing
    0.23
    scal
    0.23
    iver
    0.23
    Activations Density 0.004%

    No Known Activations