© 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. 27-TRANSCODER-HP
    7. 7851
    Prev
    Next
    INDEX
    Explanations

    Vish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    纸ä¸Ĭ
    -0.28
    æĶ¯æŁ±
    -0.27
    çİ°å®ŀ
    -0.26
    esan
    -0.25
    izons
    -0.25
    anja
    -0.24
     suscept
    -0.24
     ever
    -0.24
    elines
    -0.23
    ä¸Ńåħ³
    -0.23
    POSITIVE LOGITS
    åħįéĻ¤
    0.29
    温馨æıIJ示
    0.25
    pth
    0.25
    ãĥĭãĥ³ãĤ°
    0.25
    ytic
    0.25
     Hayward
    0.25
    warm
    0.24
    àªľ
    0.24
    .Level
    0.24
    Forge
    0.24
    Activations Density 0.011%

    No Known Activations