© 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. 89969
    Prev
    Next
    INDEX
    Explanations

    Reading

    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
    Not in Any Lists

    No Comments

    Negative Logits
    oise
    -0.28
    æĬķ票
    -0.28
     '..
    -0.28
    Friendly
    -0.25
    [âĢ¦
    -0.25
    око
    -0.25
    çĤ¹äºĨ
    -0.25
    rames
    -0.24
    帧
    -0.24
    该å¦Ĥä½ķ
    -0.24
    POSITIVE LOGITS
    sm
    0.36
     sm
    0.32
    SM
    0.28
    æ²½
    0.28
    sam
    0.28
     +
    0.27
     substant
    0.26
     Sm
    0.26
    Sm
    0.26
     generally
    0.25
    Activations Density 7.397%

    No Known Activations