© 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. 87475
    Prev
    Next
    INDEX
    Explanations

    Green

    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
    åĭģ
    -0.28
    ä¼Ĭæĸ¯
    -0.27
    æģ¶
    -0.26
    vehicles
    -0.26
    IRO
    -0.26
    onia
    -0.26
    ron
    -0.24
    orts
    -0.24
    RON
    -0.24
    iros
    -0.24
    POSITIVE LOGITS
    y
    0.30
    gnore
    0.28
    è¿ĩ
    0.26
    .Ge
    0.26
     Ge
    0.26
    份é¢Ŀ
    0.26
     nháºŃt
    0.25
    n
    0.24
    amt
    0.24
     tiá»ĥu
    0.24
    Activations Density 0.029%

    No Known Activations