© 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. 30380
    Prev
    Next
    INDEX
    Explanations

    technical/scientific writing

    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
    Negative Logits
    YTE
    -0.31
    phin
    -0.30
    ä¸Ģ家人
    -0.26
     overst
    -0.26
    eree
    -0.25
     Shore
    -0.25
    departments
    -0.24
     Requirement
    -0.24
    .sc
    -0.24
    (scanner
    -0.24
    POSITIVE LOGITS
    olla
    0.28
    éĵĬ
    0.28
    kir
    0.27
    hir
    0.26
    frei
    0.25
    è£ħ
    0.25
     session
    0.25
    roat
    0.24
    çĩİ
    0.24
     trusts
    0.24
    Activations Density 5.686%

    No Known Activations