© 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. 88269
    Prev
    Next
    INDEX
    Explanations

    sayings

    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
    CU
    -0.28
    yme
    -0.27
    orne
    -0.26
    urses
    -0.25
     layers
    -0.24
    èļ¤
    -0.24
     kali
    -0.24
     cáºŃn
    -0.24
    aday
    -0.24
    RC
    -0.24
    POSITIVE LOGITS
    ListOf
    0.27
     yourselves
    0.27
    ArrayOf
    0.26
     Probe
    0.24
    hf
    0.24
    filer
    0.24
    Pont
    0.23
    æ´»çĿĢ
    0.23
     Braz
    0.23
    olist
    0.23
    Activations Density 6.023%

    No Known Activations