© 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. 33-TRANSCODER-HP
    7. 52527
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åİħ
    -0.27
    ously
    -0.27
    廳
    -0.26
    sounds
    -0.26
    ¦
    -0.26
    Family
    -0.25
     Family
    -0.25
    æĢ»å±Ģ
    -0.25
     brun
    -0.25
    AGMENT
    -0.25
    POSITIVE LOGITS
    ijľ
    0.33
    订éĺħ
    0.26
    å®Ŀ
    0.26
    OTS
    0.26
    terr
    0.24
    è¿Ľ
    0.24
    .cf
    0.24
     pools
    0.24
     Orders
    0.24
     gauge
    0.24
    Activations Density 0.004%

    No Known Activations