© 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. 20-TRANSCODER-HP
    7. 108101
    Prev
    Next
    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refinement
    -0.27
    ctype
    -0.25
    åıij
    -0.25
    åıijçİ°
    -0.24
    æīįæĺ¯
    -0.24
    except
    -0.24
     refin
    -0.24
    Notification
    -0.24
     Pref
    -0.24
    ä»ĸ们æĺ¯
    -0.24
    POSITIVE LOGITS
    åİĿ
    0.30
    tml
    0.30
     {})↵
    0.28
    otch
    0.27
    _CHOICES
    0.26
    {}",
    0.26
    {},↵
    0.26
    ürü
    0.25
    plen
    0.25
    .dy
    0.25
    Activations Density 7.713%

    No Known Activations