© 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. 7842
    Prev
    Next
    INDEX
    Explanations

    Conjunctions

    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
    berman
    -0.27
    ä¾Ķ
    -0.26
    ä¸įæĥľ
    -0.25
    agged
    -0.25
    achat
    -0.24
    inth
    -0.24
    .rar
    -0.24
     collector
    -0.23
    ioni
    -0.23
    èĢĮåľ¨
    -0.23
    POSITIVE LOGITS
    åĽłä¸º
    1.24
     since
    1.23
     because
    1.15
    since
    1.09
    because
    1.08
    åĽłä¸ºæĪij们
    1.06
    Because
    1.03
    Since
    1.03
     Because
    1.00
     Since
    1.00
    Activations Density 0.002%

    No Known Activations