© 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. 30-TRANSCODER-HP
    7. 96780
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailer
    -0.28
    æ²±
    -0.28
    è¿ĽåĨĽ
    -0.26
    é«ĺæ½®
    -0.26
    åĪĽå§ĭ
    -0.26
    æ±²
    -0.26
    pe
    -0.25
    åĸľæ¬¢åIJĥ
    -0.25
     lee
    -0.24
    ç«Ļéķ¿
    -0.24
    POSITIVE LOGITS
    tos
    0.25
     intermediate
    0.25
    å¼Ĭ
    0.25
    åºŀ
    0.24
    atus
    0.24
    iação
    0.24
    IAN
    0.24
    adem
    0.24
    åºĦ
    0.23
     off
    0.23
    Activations Density 0.098%

    No Known Activations