© 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. 22-TRANSCODER-HP
    7. 87059
    Prev
    Next
    INDEX
    Explanations

    general news texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ---↵
    -0.27
    etros
    -0.26
    åİĿ
    -0.25
     Inf
    -0.25
    ohan
    -0.24
    ä»ĭç»įä¸Ģä¸ĭ
    -0.24
     ACA
    -0.24
    acos
    -0.24
    .dump
    -0.24
    ä¸»å¼ł
    -0.24
    POSITIVE LOGITS
     rej
    0.34
    åı¸
    0.30
    astro
    0.26
    .snp
    0.26
    snippet
    0.25
     surtout
    0.25
    ıp
    0.24
    alten
    0.24
    xffffff
    0.24
    ould
    0.24
    Activations Density 0.004%

    No Known Activations