© 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. 88960
    Prev
    Next
    INDEX
    Explanations

    Comparisons/quantities

    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
    abd
    -0.30
    åľ¨åIJĮä¸Ģ
    -0.27
    éŨæĪ·
    -0.26
     menn
    -0.26
    ould
    -0.26
    èµĽåľº
    -0.25
    ä¸Ĭåij¨
    -0.25
    @student
    -0.24
    .NEW
    -0.24
     FileMode
    -0.24
    POSITIVE LOGITS
    ances
    0.28
    èĩ´å¯Į
    0.27
     cam
    0.26
    ancias
    0.26
     ram
    0.26
    殿
    0.25
    ç®Ń
    0.25
    个
    0.25
    计åĪĴ
    0.25
    omics
    0.25
    Activations Density 14.226%

    No Known Activations