© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88935
    Prev
    Next
    INDEX
    Explanations

    computer code/text

    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
    ç½²
    -0.30
    åĭŁ
    -0.27
    ilit
    -0.27
    é¢Ĩ导
    -0.26
    ilot
    -0.24
    aro
    -0.24
    çļĦéĥ¨åĪĨ
    -0.24
     phrases
    -0.24
    èİİ
    -0.24
    ÙĤÙĪد
    -0.24
    POSITIVE LOGITS
    æ»ĭåij³
    0.29
    repid
    0.28
    é¢Ĭ
    0.26
    доÑĢов
    0.25
    resses
    0.24
    代价
    0.24
     pairwise
    0.24
     FAIL
    0.24
    hait
    0.24
     Pair
    0.24
    Activations Density 19.892%

    No Known Activations