© 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. 90089
    Prev
    Next
    INDEX
    Explanations

    convert

    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
    æĥł
    -0.27
     replicated
    -0.25
    mid
    -0.25
    _flg
    -0.24
    rena
    -0.24
    ä¸ªåĽ½å®¶
    -0.23
    Mid
    -0.23
    landers
    -0.23
    icked
    -0.23
    omy
    -0.23
    POSITIVE LOGITS
    å±Ĭ
    0.29
    lug
    0.29
    æij©æĵ¦
    0.28
     travers
    0.27
     expans
    0.27
    èŀºæĹĭ
    0.26
     drafts
    0.25
     blew
    0.25
    ?";↵
    0.24
     advent
    0.23
    Activations Density 2.067%

    No Known Activations