© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109228
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     succeed
    -0.28
    iller
    -0.28
     Bre
    -0.27
    说å®ŀ
    -0.26
    ẻ
    -0.26
     اÙĦÙħÙĨت
    -0.26
    éłĪ
    -0.25
     Success
    -0.25
     Happy
    -0.24
     ssl
    -0.24
    POSITIVE LOGITS
    å¤ļåľ°
    0.32
    .fixture
    0.31
    å¤ļä½į
    0.30
    å¤ļåIJį
    0.29
    æ¯Ĵ
    0.28
    ัà¸Ķ
    0.27
    åĨįå¤ļ
    0.27
    occer
    0.26
    å¤ļ人
    0.25
     rasp
    0.25
    Activations Density 0.926%

    No Known Activations