© 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. 87816
    Prev
    Next
    INDEX
    Explanations

    Time 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
    usta
    -0.29
    iller
    -0.26
    龸
    -0.25
    _abs
    -0.24
    å¾Ģä¸Ĭ
    -0.24
     absolut
    -0.23
    IGIN
    -0.23
     Verm
    -0.23
    áŀĴ
    -0.23
    chi
    -0.23
    POSITIVE LOGITS
    lete
    0.32
    eti
    0.31
    mage
    0.28
    èĩ¾
    0.25
     tear
    0.25
    moth
    0.25
    i
    0.25
    à¥Ģ
    0.25
    IFIC
    0.24
    èµĤ
    0.24
    Activations Density 0.005%

    No Known Activations