© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30452
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¿Ĭ
    -0.25
    onta
    -0.24
    arde
    -0.24
    缴éĶĢ
    -0.24
    raid
    -0.24
    Friendly
    -0.24
    lington
    -0.24
     impro
    -0.24
    arranty
    -0.23
    宣è¨Ģ
    -0.23
    POSITIVE LOGITS
    <{↵
    0.27
    )init
    0.26
    uin
    0.25
    亵
    0.25
    :value
    0.25
    ä½Ĩä¸įéĻIJ
    0.24
    doch
    0.24
    ][(
    0.23
    HING
    0.23
     Comm
    0.22
    Activations Density 20.866%

    No Known Activations