© 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. 107387
    Prev
    Next
    INDEX
    Explanations

    news

    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
    æĺ¯éŁ©åĽ½
    -0.26
    濯
    -0.25
    principal
    -0.25
    /pm
    -0.25
    lays
    -0.24
     nghiêm
    -0.24
    (TM
    -0.24
    wä
    -0.24
     brushes
    -0.23
    icional
    -0.23
    POSITIVE LOGITS
    身åŃIJ
    0.31
    éĢłåģĩ
    0.30
    wick
    0.28
    è¶ĭäºİ
    0.28
    ä¹Łæĺ¯å¦ĤæѤ
    0.27
    dart
    0.27
    esco
    0.27
    æľīå¾Ī大çļĦ
    0.26
    @stop
    0.25
    çĤĴä½ľ
    0.25
    Activations Density 2.537%

    No Known Activations