© 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. 129577
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    aign
    -0.29
    ä¼łåĩº
    -0.28
    -bars
    -0.27
     zwar
    -0.24
    çĶ©
    -0.24
    reserve
    -0.24
     initialise
    -0.24
    sweet
    -0.23
     departing
    -0.23
     graduating
    -0.23
    POSITIVE LOGITS
    åľ¨å¸Ĥåľºä¸Ĭ
    0.29
     ↵↵
    0.27
    è±Ĩçĵ£
    0.27
    æ³ķå®Ŀ
    0.24
     em
    0.24
    rible
    0.24
    ZO
    0.23
     Time
    0.23
    ipment
    0.23
    åĽĽå¹´
    0.23
    Activations Density 0.011%

    No Known Activations