© 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. 6364
    Prev
    Next
    INDEX
    Explanations

    Numerical data

    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
    bes
    -0.29
    jes
    -0.28
    è¡Ĺéģĵ
    -0.27
    .design
    -0.26
    ª
    -0.25
    aways
    -0.24
    ight
    -0.24
    æīĭä¸ŃçļĦ
    -0.24
     EACH
    -0.24
    zes
    -0.24
    POSITIVE LOGITS
     equ
    0.27
    è¨ĢãģĦ
    0.27
    åĮĸ
    0.26
    çĪ°
    0.26
    -assets
    0.26
    LI
    0.26
    éĩįä¸Ń
    0.25
     lent
    0.24
     wÅĤaÅĽnie
    0.24
    _timing
    0.24
    Activations Density 0.033%

    No Known Activations