© 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. 88028
    Prev
    Next
    INDEX
    Explanations

    cash

    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
     anymore
    -0.31
     necessarily
    -0.27
     NOR
    -0.27
     entire
    -0.26
    娣
    -0.26
    andas
    -0.26
     worldview
    -0.25
     ÑģобÑģÑĤвенно
    -0.25
     because
    -0.24
    åĽłä¸ºå®ĥ
    -0.24
    POSITIVE LOGITS
    ä¸įè¿ľ
    0.28
    ifton
    0.27
    iment
    0.26
    Ze
    0.26
    Sm
    0.25
    éľ¹
    0.25
     stal
    0.25
    à¹ģสà¸Ļ
    0.25
    idor
    0.24
    éľĵ
    0.24
    Activations Density 0.037%

    No Known Activations