© 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. 89332
    Prev
    Next
    INDEX
    Explanations

    scientific notation/IDs

    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
    arer
    -0.27
    ServletRequest
    -0.27
    è°ģèĥ½
    -0.24
    quin
    -0.24
     opport
    -0.24
    edium
    -0.23
    оÑĢÑĤ
    -0.23
     cach
    -0.23
    èĬ¡
    -0.23
    åįĸ家
    -0.22
    POSITIVE LOGITS
    é£İäºij
    0.25
    ishops
    0.25
    _aes
    0.24
    اÙħت
    0.24
    ãģ¡ãĤĥ
    0.24
    ç²ĺ
    0.24
     Sto
    0.24
     Computes
    0.24
     merit
    0.24
     Hof
    0.23
    Activations Density 24.680%

    No Known Activations