© 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. 18-TRANSCODER-HP
    7. 88223
    Prev
    Next
    INDEX
    Explanations

    Russian names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WhatsApp
    -0.27
     Ps
    -0.24
    fur
    -0.24
    å°ı女åŃ©
    -0.24
    _ABC
    -0.24
     Kh
    -0.23
    aidu
    -0.23
     observation
    -0.23
    Effects
    -0.23
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.23
    POSITIVE LOGITS
    croft
    0.26
    交
    0.26
    gmt
    0.25
     Bender
    0.24
    rio
    0.24
    ilage
    0.24
    è°Ħ
    0.24
    teams
    0.24
    isel
    0.24
    ERICA
    0.24
    Activations Density 8.536%

    No Known Activations