© 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. 6627
    Prev
    Next
    INDEX
    Explanations

    Studies and statistics

    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
    OOSE
    -0.26
    Ïį
    -0.23
    omba
    -0.23
    ä¿ĺ
    -0.23
     wax
    -0.23
    MLElement
    -0.23
    骰
    -0.23
    å£ĵ
    -0.23
    ohen
    -0.22
     Kul
    -0.22
    POSITIVE LOGITS
    çģŀ
    0.28
     blackout
    0.26
    idis
    0.26
    追赶
    0.25
     stint
    0.25
    çĿ£åĬŀ
    0.24
     Curt
    0.24
     altering
    0.23
     disb
    0.23
    åĶ¤
    0.23
    Activations Density 0.003%

    No Known Activations