© 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. 52588
    Prev
    Next
    INDEX
    Explanations

    Programming or web content

    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
    (link
    -0.26
    ypad
    -0.26
    amentals
    -0.25
    gies
    -0.25
    .Prop
    -0.24
    URN
    -0.24
    ycin
    -0.24
    /command
    -0.24
    cial
    -0.23
     link
    -0.23
    POSITIVE LOGITS
    å·¡åĽŀ
    0.35
    igit
    0.32
    tour
    0.30
     tour
    0.28
    å¤©åĽ½
    0.28
    å®īæĬļ
    0.27
    åĪĨæķ£
    0.26
    æ±ī
    0.26
     tours
    0.25
     Tour
    0.25
    Activations Density 0.001%

    No Known Activations