© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53751
    Prev
    Next
    INDEX
    Explanations

    Charles

    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
    Not in Any Lists

    No Comments

    Negative Logits
     poet
    -0.54
     Poetry
    -0.52
     poetic
    -0.50
    æĸĩåѦ
    -0.49
    è¯Ĺ人
    -0.48
     poetry
    -0.48
     poem
    -0.48
    è¯ĹæŃĮ
    -0.47
    è¯Ĺ
    -0.47
     poems
    -0.46
    POSITIVE LOGITS
    :^
    0.28
    综åIJĪæĢ§
    0.28
    ãģıãĤĮ
    0.26
    иде
    0.26
    å¡«è¡¥
    0.26
     ISIL
    0.25
    çīº
    0.25
     sink
    0.25
    usted
    0.24
     incom
    0.24
    Activations Density 0.159%

    No Known Activations