© 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. 111883
    Prev
    Next
    INDEX
    Explanations

    es

    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
    edList
    -0.32
    æīįç®Ĺ
    -0.31
    WithData
    -0.26
    åĭŁéĽĨèµĦéĩij
    -0.24
    naments
    -0.23
     cheers
    -0.23
    ionales
    -0.23
    票
    -0.23
    èĢģæĿ¿
    -0.23
    ynchronously
    -0.23
    POSITIVE LOGITS
    angan
    0.28
     many
    0.28
    aly
    0.27
    鸳
    0.26
    ubi
    0.25
     Many
    0.25
     Fri
    0.25
    ou
    0.24
    许å¤ļ
    0.24
    ub
    0.24
    Activations Density 0.007%

    No Known Activations