© 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. 87504
    Prev
    Next
    INDEX
    Explanations

    internet article excerpts

    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
     Budd
    -0.26
    inese
    -0.26
    ])]
    -0.25
    åĸĦæĦı
    -0.25
    æĿ¡
    -0.25
    åĪĨæĶ¯
    -0.24
    åŁİåĮº
    -0.24
    locks
    -0.24
     ano
    -0.24
    å½Ĵ
    -0.24
    POSITIVE LOGITS
    andal
    0.30
    specs
    0.29
     presently
    0.28
    efully
    0.27
    currently
    0.27
     currently
    0.27
    aldi
    0.27
    ä»ĸæĽ¾
    0.26
    isposable
    0.25
    鸪
    0.25
    Activations Density 0.003%

    No Known Activations