© 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. 30-TRANSCODER-HP
    7. 95798
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [val
    -0.26
     val
    -0.26
     vals
    -0.25
    uplicate
    -0.25
    RIX
    -0.24
    ptide
    -0.24
    PageIndex
    -0.23
    éħŀ
    -0.23
     Sands
    -0.23
    para
    -0.23
    POSITIVE LOGITS
    versions
    0.30
    åĮº
    0.29
    ê°Ħ
    0.29
    鬼
    0.28
    åijĬçŁ¥
    0.26
    kol
    0.25
    çĶŁ
    0.25
    æ²»æĦĪ
    0.25
    èĢ¿
    0.24
     Approach
    0.24
    Activations Density 0.886%

    No Known Activations