© 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. 23470
    Prev
    Next
    INDEX
    Explanations

    obligation

    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
    ocol
    -0.28
    åĩºåħ¥å¢ĥ
    -0.28
    atility
    -0.27
     ör
    -0.25
    尤为éĩįè¦ģ
    -0.25
    unami
    -0.24
    icularly
    -0.24
     stressing
    -0.24
    绿水éĿĴå±±
    -0.23
     attacking
    -0.23
    POSITIVE LOGITS
    票
    0.28
    æĬĬæĪij
    0.26
    é¼ł
    0.26
    åIJ¬è¯´è¿ĩ
    0.26
    DR
    0.25
    ACLE
    0.25
    åŃļ
    0.24
    ft
    0.24
    ess
    0.24
    lover
    0.24
    Activations Density 0.023%

    No Known Activations