© 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. 130622
    Prev
    Next
    INDEX
    Explanations

    Computer settings and options

    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
    sur
    -0.24
     fr
    -0.24
    éĢĢåĽŀ
    -0.24
     turnover
    -0.24
    su
    -0.23
    %@
    -0.23
     Ying
    -0.23
    ãģĦãģ¾ãģĻãģĮ
    -0.23
    dex
    -0.23
    ä¹łæĥ¯
    -0.23
    POSITIVE LOGITS
    ovable
    0.28
    å±ij
    0.27
    egg
    0.27
    	resource
    0.24
    èIJ©
    0.24
     Physiology
    0.24
    èĬį
    0.24
    Ĥ¤
    0.24
    (option
    0.23
    Lens
    0.23
    Activations Density 0.098%

    No Known Activations