© 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. 98726
    Prev
    Next
    INDEX
    Explanations

    website settings

    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
    à¹Ģลย
    -0.26
    å¥Ķ
    -0.25
    etta
    -0.25
     disconnect
    -0.25
    ections
    -0.25
     stuff
    -0.25
     reconnect
    -0.25
    eld
    -0.24
    æĬķæłĩ人
    -0.24
    åī©ä¸ĭ
    -0.24
    POSITIVE LOGITS
    åķĨä¸ļåĮĸ
    0.28
    Ñĩи
    0.25
    ress
    0.24
    èĬ
    0.24
     compromise
    0.24
    并éĿŀ
    0.23
    å±Ĥåĩº
    0.23
     }};↵
    0.23
     GPLv
    0.23
     Harden
    0.22
    Activations Density 0.008%

    No Known Activations