© 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. 9654
    Prev
    Next
    INDEX
    Explanations

    a

    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
    enc
    -0.28
    å¼ĢæĶ¾å¼ı
    -0.28
    och
    -0.28
    мÑĭÑĪ
    -0.27
     Tá»ķ
    -0.27
    stroy
    -0.26
    éĤ£ç§į
    -0.26
    islation
    -0.25
     Mexicans
    -0.25
     Encounter
    -0.25
    POSITIVE LOGITS
     anonymity
    0.27
    åĹ¡
    0.27
    ano
    0.27
     ping
    0.26
    åıĤçħ§
    0.26
     banker
    0.25
    åįļä¼ļ
    0.25
     streak
    0.25
    ?id
    0.25
     void
    0.25
    Activations Density 0.001%

    No Known Activations