© 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. 111815
    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
    oupper
    -0.27
    åĪ°äºĨ
    -0.25
    invert
    -0.25
    ury
    -0.24
    å°±æĺ¯è¦ģ
    -0.24
    iline
    -0.23
    иÑĤелÑĮн
    -0.23
    åıĮåIJij
    -0.23
    DBG
    -0.23
     contours
    -0.23
    POSITIVE LOGITS
    å¥Ĺ
    0.29
    è¿·
    0.29
    еÑĩение
    0.28
    äºı
    0.28
     delta
    0.24
    èħIJèļĢ
    0.24
    Jam
    0.24
    pressed
    0.24
    å·¾
    0.24
    ä½İä¼°
    0.24
    Activations Density 0.004%

    No Known Activations