© 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. 111828
    Prev
    Next
    INDEX
    Explanations

    at

    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
    ä¼ģä¸ļæıIJä¾Ľ
    -0.28
    _esc
    -0.26
    rene
    -0.26
    lient
    -0.26
    RLF
    -0.25
    翳
    -0.25
    èĩ»
    -0.24
    nearest
    -0.24
     Esc
    -0.24
    该æĢİä¹ĪåĬŀ
    -0.24
    POSITIVE LOGITS
     cost
    0.54
    cost
    0.52
     inexpensive
    0.48
    æĪIJæľ¬
    0.46
     costs
    0.45
    çļĦæĪIJæľ¬
    0.44
    _cost
    0.43
    Cost
    0.42
    è´¹çĶ¨
    0.42
     easy
    0.42
    Activations Density 0.011%

    No Known Activations