© 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. 22-TRANSCODER-HP
    7. 98298
    Prev
    Next
    INDEX
    Explanations

    code and version markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addock
    -0.32
    idan
    -0.26
    çĬ¹å¦Ĥ
    -0.24
    éªŀ
    -0.24
    \\/
    -0.24
     cross
    -0.24
    opot
    -0.23
    ixture
    -0.23
    æĪª
    -0.23
     disp
    -0.23
    POSITIVE LOGITS
    UCT
    0.28
    NON
    0.27
    cul
    0.26
    Lastly
    0.26
    ft
    0.26
     `{
    0.25
    çĴĢ
    0.25
    iÄį
    0.25
    ãĥķãĥĪ
    0.24
     curriculum
    0.24
    Activations Density 0.011%

    No Known Activations