© 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. 8622
    Prev
    Next
    INDEX
    Explanations

    detecting noisy/unstructured text

    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
     -:
    -0.28
    éĿĻæĢģ
    -0.26
    .shtml
    -0.25
     Lack
    -0.25
    éĤł
    -0.25
     lack
    -0.25
    çIJ¯
    -0.24
    åĶ±æŃĮ
    -0.24
     Bearing
    -0.24
    å°ģè£ħ
    -0.24
    POSITIVE LOGITS
     promot
    0.27
    ãĤīãģĽ
    0.27
    illard
    0.27
    代çIJĨ人
    0.26
     contag
    0.25
     Directors
    0.25
    .piece
    0.24
    ä¼ĹæīĢ
    0.24
    LabelText
    0.24
    alars
    0.24
    Activations Density 0.912%

    No Known Activations