© 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. 90006
    Prev
    Next
    INDEX
    Explanations

    genetics

    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
    prior
    -0.28
    æīĵå¼Ģ
    -0.27
    :hidden
    -0.27
    æīĵæĬĺ
    -0.26
    asty
    -0.26
     Positioned
    -0.26
    æīĵå¼ĢäºĨ
    -0.25
    geois
    -0.25
     libertin
    -0.24
    depend
    -0.24
    POSITIVE LOGITS
    ÙĪÙĦا
    0.26
     sustained
    0.25
    ãģ§ãĤĤ
    0.25
    олж
    0.24
    qing
    0.24
     SES
    0.24
    redients
    0.24
    nung
    0.24
    å¾ģéĽĨ
    0.24
    çļĦèī¯å¥½
    0.23
    Activations Density 6.461%

    No Known Activations