© 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. 87743
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
    çīĮçħ§
    -0.27
     Hi
    -0.26
     incarn
    -0.26
    ä½ĵçİ°åĩº
    -0.26
     setUsername
    -0.25
    built
    -0.24
    æĶĺ
    -0.24
    å½¢æĢģ
    -0.24
    èī¯å¥½
    -0.23
    æĺ¾ç¤ºåĩº
    -0.23
    POSITIVE LOGITS
    å°ıå°ı
    0.28
    .TabStop
    0.28
    Fans
    0.27
     fool
    0.26
     pretending
    0.25
     views
    0.25
    acad
    0.25
    urrencies
    0.24
    çĶ¨å¿ĥ
    0.24
     FAG
    0.24
    Activations Density 0.005%

    No Known Activations