© 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. 130110
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    upper
    -0.27
     excer
    -0.27
    个人è§ĤçĤ¹
    -0.25
    above
    -0.25
    eced
    -0.25
    çĥ¦èºģ
    -0.24
     starred
    -0.24
     upper
    -0.24
    并åıij
    -0.24
    éĥ¨åĪĨåĨħ容
    -0.23
    POSITIVE LOGITS
    Mir
    0.28
    æĿŁ
    0.27
     Mir
    0.26
    éŀĺ
    0.26
    nat
    0.25
    æĸĻ
    0.25
     меÑĢ
    0.24
     Measure
    0.24
     tumble
    0.24
    ÑĪи
    0.24
    Activations Density 0.018%

    No Known Activations