© 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. 98455
    Prev
    Next
    INDEX
    Explanations

    4

    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
     tide
    -0.27
    oka
    -0.26
    batch
    -0.25
    umpt
    -0.25
    iter
    -0.25
    ividual
    -0.24
     batches
    -0.24
    人æīį
    -0.24
    æ·¦
    -0.24
    eter
    -0.24
    POSITIVE LOGITS
    è¿ĺ以为
    0.27
    å½¢å¼ı
    0.24
    åĽłä¸ºå¥¹
    0.24
    Îı
    0.24
    pto
    0.24
    çļĦå½¢å¼ı
    0.24
     Gle
    0.23
    rô
    0.23
    ELSE
    0.23
    è¦ģçľĭ
    0.22
    Activations Density 0.002%

    No Known Activations