© 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. 27-TRANSCODER-HP
    7. 9726
    Prev
    Next
    INDEX
    Explanations

    MRI

    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
    Negative Logits
    /apis
    -0.28
    onic
    -0.27
    PerPage
    -0.26
    thest
    -0.26
    acades
    -0.25
    è¯ļ
    -0.25
    CUS
    -0.25
    alytics
    -0.24
    alphabet
    -0.24
    ÑĤика
    -0.24
    POSITIVE LOGITS
    -trigger
    0.28
    éľľ
    0.25
    agli
    0.25
    æĺķ
    0.24
    ç§ij
    0.24
    vo
    0.23
     overd
    0.23
     hotline
    0.23
    reservation
    0.23
    .reserve
    0.23
    Activations Density 0.037%

    No Known Activations