© 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. 9-TRANSCODER-HP
    7. 29407
    Prev
    Next
    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ·
    -0.29
    æĬ¬
    -0.27
    ernal
    -0.26
     Civil
    -0.25
    ingo
    -0.24
    æ°ijçĶ¨
    -0.24
    ìĤ¬
    -0.24
    æļ
    -0.23
    æł¹æľ¬
    -0.23
     Gaines
    -0.23
    POSITIVE LOGITS
    osas
    0.26
     cooler
    0.26
    adol
    0.26
    pieces
    0.25
    èĢĮæĪIJ
    0.25
    åĪĩ
    0.25
     Naz
    0.25
    åĩı
    0.24
    abox
    0.24
    wort
    0.24
    Activations Density 2.361%

    No Known Activations