© 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. 88118
    Prev
    Next
    INDEX
    Explanations

    beetle or beet

    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
    aison
    -0.28
    ced
    -0.27
    elastic
    -0.26
    plete
    -0.26
    ied
    -0.25
    ous
    -0.25
    ouse
    -0.25
    amel
    -0.24
    åıł
    -0.24
    istrate
    -0.24
    POSITIVE LOGITS
    zers
    0.28
     uniforms
    0.26
    gers
    0.25
    寥
    0.25
    nor
    0.25
     trailers
    0.25
     privileges
    0.25
    æĹħ游å±Ģ
    0.24
    åİŁä¾Ĩ
    0.24
    Rua
    0.23
    Activations Density 12.223%

    No Known Activations