© 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. 58531
    Prev
    Next
    INDEX
    Explanations

    ci

    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
    agne
    -0.29
    s
    -0.27
    agem
    -0.27
    æĦĨ
    -0.26
    dent
    -0.25
    rips
    -0.25
    rition
    -0.24
     Continent
    -0.24
     dur
    -0.23
    arded
    -0.23
    POSITIVE LOGITS
    ensor
    0.28
    Å¡t
    0.27
    Poss
    0.24
    tracker
    0.23
     ones
    0.23
    rust
    0.23
    éĢĢåĩº
    0.23
    icate
    0.23
    éĻĭ
    0.23
     możliwe
    0.23
    Activations Density 0.004%

    No Known Activations