© 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. 98896
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    åıŁ
    -0.27
     же
    -0.27
     ...↵
    -0.26
     ingredient
    -0.25
    å««
    -0.24
     caught
    -0.24
    åľ¨è¿ĩ渡
    -0.24
    ...↵
    -0.23
     parameter
    -0.23
     UNESCO
    -0.23
    POSITIVE LOGITS
    proved
    0.26
    ä½ĵç³»
    0.25
    ollo
    0.25
    æī£
    0.25
    èĭ±çī¹
    0.24
    ",↵↵
    0.24
    etics
    0.24
    athy
    0.24
    ";↵↵
    0.23
    ç¼Ķ
    0.23
    Activations Density 0.004%

    No Known Activations