© 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. 27-TRANSCODER-HP
    7. 56448
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     mob
    -0.27
    ord
    -0.27
    [axis
    -0.26
    æİ¥è¿ij
    -0.25
    ä¸ĸä¸Ĭ
    -0.25
    ampo
    -0.25
    å¿ĥ缮
    -0.25
    _epoch
    -0.25
    为人
    -0.24
    orus
    -0.24
    POSITIVE LOGITS
    icing
    0.25
    anced
    0.25
    erness
    0.25
     Default
    0.25
     design
    0.24
    Default
    0.24
    default
    0.24
    olation
    0.24
    é»ĺ认
    0.23
    legates
    0.23
    Activations Density 0.001%

    No Known Activations