© 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. 30-TRANSCODER-HP
    7. 96773
    Prev
    Next
    INDEX
    Explanations

    eye diseases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spe
    -0.27
    åįĬå²Ľ
    -0.26
     Susp
    -0.26
    Susp
    -0.25
     PUB
    -0.25
    pain
    -0.24
    writers
    -0.24
    ARSE
    -0.24
    semb
    -0.23
    &view
    -0.23
    POSITIVE LOGITS
    icks
    0.29
    å¹²
    0.27
    é¢Ħè¨Ģ
    0.26
    AGES
    0.25
    _binary
    0.25
    Č↵
    0.25
    othy
    0.24
     Astr
    0.24
     dry
    0.24
    ucker
    0.24
    Activations Density 0.102%

    No Known Activations