© 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. 88803
    Prev
    Next
    INDEX
    Explanations

    Start of texts

    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
    ายà¸Ļ
    -0.27
    ArrayOf
    -0.27
    zet
    -0.26
    elix
    -0.25
    |--
    -0.24
     Alma
    -0.24
    ä¸įåĪĨ
    -0.24
    å°¤
    -0.23
    ä¹Łæĺ¯å¦ĤæѤ
    -0.23
    à¸ĺร
    -0.23
    POSITIVE LOGITS
    iter
    0.26
    çĸ¤
    0.26
    itations
    0.25
    vard
    0.25
    åĪ©äºİ
    0.25
    opy
    0.25
    .FR
    0.24
    çĽĺ
    0.24
    fr
    0.24
    osity
    0.23
    Activations Density 33.006%

    No Known Activations