© 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. 89351
    Prev
    Next
    INDEX
    Explanations

    science/technology

    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
    å¾Ģ
    -0.24
    abs
    -0.24
    orphic
    -0.24
    qui
    -0.24
    -Compatible
    -0.23
     pouch
    -0.23
    æ¶ĪèĢĹ
    -0.23
    ORE
    -0.22
     coz
    -0.22
    .pow
    -0.22
    POSITIVE LOGITS
    æŀ¸
    0.26
     (::
    0.24
    缸åħ³äººåijĺ
    0.24
    éĥ½çŁ¥éģĵ
    0.24
    身为
    0.24
    å°±
    0.24
    anut
    0.23
    enuity
    0.23
    åľ¬
    0.23
    =~
    0.23
    Activations Density 81.498%

    No Known Activations