© 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. 111956
    Prev
    Next
    INDEX
    Explanations

    you

    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
    ä»ĸ们ä¼ļ
    -0.30
    åĨħå¤ĸ
    -0.28
    antly
    -0.28
    tement
    -0.28
    å¤ļå°ij
    -0.28
    åıĪ好
    -0.26
    -ended
    -0.26
    -Based
    -0.25
    mente
    -0.25
    天ä¸ĭ
    -0.25
    POSITIVE LOGITS
     noticed
    0.29
    igit
    0.28
     notice
    0.28
     Iranians
    0.28
    ’re
    0.28
    /she
    0.27
    IID
    0.26
    RIX
    0.26
    çĶŁæ´»çļĦ
    0.25
     can
    0.25
    Activations Density 0.822%

    No Known Activations