© 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. 88496
    Prev
    Next
    INDEX
    Explanations

    Article excerpts

    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
    ëħ¼
    -0.26
     åĩ
    -0.25
     lý
    -0.25
    ä¹ĭæīĢ以
    -0.25
    Merit
    -0.24
    åĨĮ
    -0.24
     factors
    -0.24
     intentionally
    -0.24
     abstract
    -0.24
    éĢ»
    -0.24
    POSITIVE LOGITS
    pest
    0.30
    çĻĤ
    0.28
    éĹ®é¢ĺæĺ¯
    0.27
    ,),↵
    0.26
    igne
    0.26
    è¡Įä¸ļåįıä¼ļ
    0.26
    æĢİä¹ĪåĬŀ
    0.25
    .'),↵
    0.25
    ."},↵
    0.24
    æĺ¯ä»Ģä¹Ī
    0.24
    Activations Density 7.541%

    No Known Activations