© 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. 87729
    Prev
    Next
    INDEX
    Explanations

    Age

    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
    éĽĩä½£
    -0.25
    igators
    -0.24
    óż
    -0.24
    çģµæ°Ķ
    -0.23
    éĤ£äºĽ
    -0.23
     flashes
    -0.23
    dfa
    -0.23
     basil
    -0.23
    ancia
    -0.23
    é»ijçĻ½
    -0.23
    POSITIVE LOGITS
    以ä¸Ĭ
    0.85
    以ä¸ĬçļĦ
    0.82
    åıĬ以ä¸Ĭ
    0.69
    以ä¸Ĭãģ®
    0.67
    以ä¸ĬåѦåİĨ
    0.56
     ìĿ´ìĥģ
    0.54
     above
    0.53
    级以ä¸Ĭ
    0.51
    以ä¸ĭ
    0.48
    以æĿ¥
    0.47
    Activations Density 0.044%

    No Known Activations