© 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. 112132
    Prev
    Next
    INDEX
    Explanations

    Code licenses and programming

    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
    ive
    -0.28
    dd
    -0.27
    uard
    -0.27
    hr
    -0.27
    æ²ī
    -0.25
    -tax
    -0.25
     match
    -0.25
    MAL
    -0.25
    交ä»ĺ
    -0.25
    å¸ĥ
    -0.24
    POSITIVE LOGITS
    quests
    0.28
    åľ¨æĪijåĽ½
    0.26
    аниз
    0.26
    +Sans
    0.25
     dispenser
    0.25
    该游æĪı
    0.25
    è¿Ļå¼ł
    0.25
    èĭ±çī¹
    0.24
    (resolve
    0.24
    claimer
    0.24
    Activations Density 0.016%

    No Known Activations