© 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. 87859
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     Lik
    -0.25
    oyal
    -0.25
     gs
    -0.25
     InputStreamReader
    -0.24
     fellow
    -0.24
    -kit
    -0.24
     lunch
    -0.24
     null
    -0.23
     Kit
    -0.23
    GS
    -0.23
    POSITIVE LOGITS
    ä»ĸ说
    0.26
     اÙĦØ£ÙĪÙĦ
    0.25
    пÑĢоÑģ
    0.25
    Through
    0.24
    tries
    0.24
    charges
    0.24
    åĬ¨éĿĻ
    0.24
    ä¸Ńå°ıåŀĭ
    0.24
    ãĤ¹ãĥĶ
    0.23
    oppers
    0.23
    Activations Density 0.034%

    No Known Activations