© 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. 25-TRANSCODER-HP
    7. 108261
    Prev
    Next
    INDEX
    Explanations

    grade, quality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bundle
    -0.28
    éľĩ
    -0.25
    Bundle
    -0.25
    æ°Ķåij³
    -0.25
     Stanford
    -0.24
    èĺħ
    -0.24
    panion
    -0.24
    è°ĥåīĤ
    -0.24
    éĻĮçĶŁäºº
    -0.24
    inode
    -0.24
    POSITIVE LOGITS
    -grade
    0.74
     grade
    0.69
    级
    0.68
     Grade
    0.63
    Grade
    0.58
    -quality
    0.56
     quality
    0.55
    .grade
    0.52
    级åĪ«çļĦ
    0.52
    grade
    0.51
    Activations Density 2.064%

    No Known Activations