© 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. 23-TRANSCODER-HP
    7. 25448
    Prev
    Next
    INDEX
    Explanations

    conflicts and allegiances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    unbind
    -0.30
    .fromJson
    -0.26
    >Lorem
    -0.26
    .isSuccess
    -0.26
     disag
    -0.25
    oks
    -0.25
    lectric
    -0.25
     lòng
    -0.24
    otope
    -0.24
    icle
    -0.23
    POSITIVE LOGITS
    ÑĩеÑģÑĤво
    0.27
    åķĨä¼ļ
    0.27
    æ±
    0.26
    %x
    0.26
    å°ıçĻ½
    0.25
     capitalized
    0.24
     pymysql
    0.24
    .Logger
    0.23
    åİĮ
    0.23
    鼷
    0.23
    Activations Density 0.005%

    No Known Activations