© 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. 27-TRANSCODER-HP
    7. 56918
    Prev
    Next
    INDEX
    Explanations

    Numerical data and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _verbose
    -0.26
    æij¸
    -0.25
     touches
    -0.25
    ä¸Ģ线
    -0.25
    antha
    -0.25
     crypt
    -0.25
    Concat
    -0.24
     ÐĶе
    -0.24
    åĮł
    -0.24
    quer
    -0.23
    POSITIVE LOGITS
    åĪĩåħ¥
    0.28
    iya
    0.25
    ä¸įæĸŃçļĦ
    0.24
     luego
    0.24
    ary
    0.24
    çīĪ
    0.24
    ä¸įåģľçļĦ
    0.24
    edition
    0.23
    ely
    0.23
    å¸Ī
    0.23
    Activations Density 0.005%

    No Known Activations