© 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. 88715
    Prev
    Next
    INDEX
    Explanations

    End of sentences/code

    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
    '+↵
    -0.29
     +=↵
    -0.25
    æĭ¥
    -0.25
    ارة
    -0.24
     Cann
    -0.24
    éĩįä¸Ń
    -0.24
     $↵↵
    -0.24
     Capitol
    -0.24
    æĦıæĢĿ
    -0.24
     **↵
    -0.23
    POSITIVE LOGITS
     groups
    0.25
    åIJ¬å®Į
    0.25
    ilateral
    0.25
     Concept
    0.24
    res
    0.24
    Reviewed
    0.24
    æ®ĭ
    0.24
    alte
    0.24
    uck
    0.23
    endent
    0.23
    Activations Density 65.323%

    No Known Activations