© 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. 9766
    Prev
    Next
    INDEX
    Explanations

    on

    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
     withRouter
    -0.32
     ready
    -0.31
     feeling
    -0.31
     Ready
    -0.30
     with
    -0.29
     having
    -0.28
     wanting
    -0.28
     pedig
    -0.27
     needing
    -0.27
    with
    -0.26
    POSITIVE LOGITS
     earth
    0.69
    earth
    0.63
     Earth
    0.62
    åľ°çIJĥ
    0.55
    Earth
    0.53
    -earth
    0.52
    åľ°çIJĥä¸Ĭ
    0.45
    å¤§åľ°
    0.33
     earthly
    0.28
    éĿ¢
    0.28
    Activations Density 0.004%

    No Known Activations