© 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. 30-TRANSCODER-HP
    7. 94928
    Prev
    Next
    INDEX
    Explanations

    comic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Pix
    -0.28
    allest
    -0.27
    plied
    -0.27
    å±ıå¹ķä¸Ĭ
    -0.26
    å©¿
    -0.26
     Enumerator
    -0.25
    åijĺ
    -0.25
    rpc
    -0.25
    é¢Ŀ度
    -0.25
    screen
    -0.25
    POSITIVE LOGITS
    inated
    0.28
    çݰ代çī©æµģ
    0.27
    -present
    0.27
     muddy
    0.27
     bin
    0.26
    esture
    0.26
    åIJ¬çĿĢ
    0.25
    OPS
    0.25
     wrought
    0.25
    thetic
    0.25
    Activations Density 0.889%

    No Known Activations