© 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. 9649
    Prev
    Next
    INDEX
    Explanations

    Research/Code

    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
    çµķå°į
    -0.28
    erland
    -0.26
    eing
    -0.26
    TPL
    -0.25
    isted
    -0.25
    ä¹Łä¸įéĶĻ
    -0.25
    owa
    -0.24
    ç»Ŀ对
    -0.24
    _TP
    -0.24
    orna
    -0.24
    POSITIVE LOGITS
    meta
    0.29
    çİĦ
    0.28
    个人
    0.27
    çIJĨ
    0.26
    ä¸īå±Ĥ
    0.25
    è¿İ
    0.24
    ç²Ł
    0.24
    æ¿Ģæ´»
    0.24
    Em
    0.24
     cach
    0.24
    Activations Density 0.909%

    No Known Activations