© 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. 25344
    Prev
    Next
    INDEX
    Explanations

    the

    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
    éľĢæ±Ĥ
    -0.29
    壶
    -0.28
     quickest
    -0.26
    kom
    -0.25
    oux
    -0.25
     onder
    -0.25
     fastest
    -0.25
    ç»ĪçĤ¹
    -0.24
    çĶ³æĬ¥
    -0.24
    ä¸ĭåĪĹ
    -0.24
    POSITIVE LOGITS
    tees
    0.30
    çļĦåģļæ³ķ
    0.27
    advert
    0.26
    unte
    0.26
    fds
    0.25
     fds
    0.25
     similarly
    0.25
    hear
    0.24
    _way
    0.24
    è¿Ļç§įæĥħåĨµ
    0.23
    Activations Density 0.004%

    No Known Activations