© 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. 7889
    Prev
    Next
    INDEX
    Explanations

    technical/numerical data

    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
     corners
    -0.28
    æľ½
    -0.27
    ier
    -0.26
    RICS
    -0.26
     ain
    -0.26
    kind
    -0.24
     prem
    -0.23
    è¾Ĭ
    -0.23
    èĪį
    -0.23
     Ain
    -0.23
    POSITIVE LOGITS
    wap
    0.29
    mony
    0.27
    apons
    0.27
    éĨ®
    0.26
    èijŃ
    0.26
     Sag
    0.26
    èµĦæºIJéħįç½®
    0.26
    пад
    0.25
    @mail
    0.25
    Reach
    0.25
    Activations Density 0.016%

    No Known Activations