© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7516
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°ıå·§
    -0.28
    straction
    -0.27
    -sl
    -0.26
    çļĦä¼Łå¤§
    -0.26
    roe
    -0.26
     CURL
    -0.25
    å®ĺ
    -0.25
     tackled
    -0.25
     minded
    -0.24
     simul
    -0.24
    POSITIVE LOGITS
     agree
    0.25
    åİ»çľĭ
    0.25
     oblig
    0.24
     implies
    0.24
     mirrors
    0.24
     Gaw
    0.24
    baugh
    0.24
    istine
    0.24
     acknowled
    0.24
    æīģ
    0.24
    Activations Density 0.015%

    No Known Activations