© 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. 112563
    Prev
    Next
    INDEX
    Explanations

    software

    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
    èIJ¥ä¸ļé¢Ŀ
    -0.29
    wald
    -0.26
    endphp
    -0.24
    iples
    -0.24
    chner
    -0.24
    uki
    -0.24
    hausen
    -0.24
    kü
    -0.24
     jur
    -0.23
     '}
    -0.23
    POSITIVE LOGITS
    çľĭå¾ħ
    0.28
    Delta
    0.28
    å¾ĹçĽĬ
    0.27
    èĸĦ
    0.26
    åij³
    0.26
    èĢĮéĿŀ
    0.25
     :-)
    0.25
    åĴĮè°IJ
    0.25
    ãģĤãĤĬ
    0.25
    .Parse
    0.25
    Activations Density 0.000%

    No Known Activations