© 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. 24-TRANSCODER-HP
    7. 151227
    Prev
    Next
    INDEX
    Explanations

    Foreign language names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Tyson
    -0.28
    otec
    -0.27
    ëįĺ
    -0.26
     cảnh
    -0.26
     Accord
    -0.25
     forwards
    -0.25
    çĿĢçľ¼
    -0.24
    panion
    -0.24
    头èĦij
    -0.23
    бо
    -0.23
    POSITIVE LOGITS
    æ´Ĵ
    0.27
    çĥĪ
    0.25
    onomy
    0.24
    èµĽ
    0.24
    æĴĴ
    0.24
    <const
    0.23
     uri
    0.23
    äºĮåįģåĽĽ
    0.23
     piss
    0.23
    åįķ车
    0.23
    Activations Density 0.505%

    No Known Activations