© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5078
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    ä¸ĢæĹı
    -0.27
    aguay
    -0.27
     xi
    -0.26
     undone
    -0.25
    isson
    -0.25
    __,↵
    -0.25
    üc
    -0.25
    eworld
    -0.24
     Walton
    -0.23
    emax
    -0.23
    POSITIVE LOGITS
     legit
    0.28
     REPL
    0.27
    ev
    0.26
    eer
    0.25
    çĭ®
    0.25
    MethodManager
    0.25
    Rep
    0.25
    oria
    0.24
    ei
    0.24
     professionally
    0.24
    Activations Density 0.005%

    No Known Activations