© 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. 32-TRANSCODER-HP
    7. 40900
    Prev
    Next
    INDEX
    Explanations

    say parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ant
    -0.71
     Ant
    -0.68
    Ant
    -0.59
     ant
    -0.58
    _ant
    -0.57
    antic
    -0.57
     antig
    -0.57
     antic
    -0.55
    æĬĹ
    -0.54
     antiqu
    -0.54
    POSITIVE LOGITS
    hoa
    0.29
    é¹Ĥ
    0.27
    }))
    0.27
     kho
    0.27
    ))).
    0.27
    )))
    0.26
    ))),↵
    0.25
    "]))
    0.25
    åĶIJæľĿ
    0.25
    yth
    0.25
    Activations Density 0.009%

    No Known Activations