© 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. 12-TRANSCODER-HP
    7. 24153
    Prev
    Next
    INDEX
    Explanations

    opia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å©¿
    -0.27
    ardi
    -0.27
     Honour
    -0.26
     STATES
    -0.26
    .states
    -0.25
    ç¼ī
    -0.25
    æºī
    -0.24
     states
    -0.24
    heimer
    -0.23
    Ñıз
    -0.23
    POSITIVE LOGITS
    èĥĮ
    0.30
    ä¹Łä¸įéĶĻ
    0.27
     primitive
    0.27
    ?"↵
    0.26
    /videos
    0.26
     incidental
    0.25
    设æĸ½
    0.24
    å¾Īå¤ļ人
    0.24
    ETS
    0.23
    룩
    0.23
    Activations Density 0.002%

    No Known Activations