© 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. 95195
    Prev
    Next
    INDEX
    Explanations

    near

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -low
    -0.27
     inside
    -0.27
    =device
    -0.26
    ully
    -0.26
     densities
    -0.25
     arrangements
    -0.24
    uur
    -0.24
     carbon
    -0.23
    Īĺ
    -0.23
    -other
    -0.23
    POSITIVE LOGITS
    è¿IJ
    0.31
    çİ°
    0.29
    lü
    0.27
     Hiá»ĩn
    0.26
    çģµ
    0.26
     Futures
    0.26
     hẹn
    0.26
    vi
    0.25
     Committee
    0.25
    vim
    0.25
    Activations Density 0.050%

    No Known Activations