© 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. 89883
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    inters
    -0.33
     TER
    -0.27
     ter
    -0.27
    contents
    -0.27
    æĬij
    -0.26
    åŀł
    -0.24
    åį·
    -0.24
     yap
    -0.24
    缺
    -0.24
    åŃIJåŃĻ
    -0.23
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.25
    idenav
    0.25
    áºł
    0.25
     Armour
    0.25
    èħ¹æ³»
    0.25
    æľīä¸Ģä½į
    0.24
    éĢ¼è¿ij
    0.24
    /linux
    0.24
    /org
    0.24
    éĻĽä¸ĭ
    0.23
    Activations Density 14.674%

    No Known Activations