© 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. 25351
    Prev
    Next
    INDEX
    Explanations

    Articles ("a", "an")

    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
     mixture
    -0.28
    çİĩ为
    -0.27
    isse
    -0.25
    æķĪ
    -0.25
    bsp
    -0.25
    æŀĭ
    -0.24
     Trib
    -0.24
     Pocket
    -0.24
    ì»
    -0.24
    åĪĨ离
    -0.24
    POSITIVE LOGITS
    ani
    0.31
     thing
    0.28
    é¡¹çĽ®çļĦ
    0.26
    æĽ´å¤ļ
    0.26
    orie
    0.26
    åijĬè¯ī她
    0.26
    亿
    0.25
    clid
    0.25
    __("
    0.24
    åĶIJ
    0.24
    Activations Density 0.008%

    No Known Activations