© 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. 112126
    Prev
    Next
    INDEX
    Explanations

    Titles and Instructions

    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
    åIJij社ä¼ļ
    -0.27
    容
    -0.27
    gram
    -0.26
    umer
    -0.26
    weep
    -0.26
    ment
    -0.25
    prec
    -0.24
    fe
    -0.24
    itor
    -0.23
    lic
    -0.23
    POSITIVE LOGITS
    пиÑģÑĮ
    0.23
    åĻİ
    0.23
    éĥ¨éķ¿
    0.22
    ettel
    0.22
    omap
    0.22
    ä¹ĭ乡
    0.22
    xmm
    0.22
     пÑĢез
    0.22
    MISS
    0.22
    _ASSOC
    0.22
    Activations Density 0.010%

    No Known Activations