© 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. 32-TRANSCODER-HP
    7. 42192
    Prev
    Next
    INDEX
    Explanations

    help

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Äijá»Ŀi
    -0.27
     Zuk
    -0.27
     life
    -0.27
    ynes
    -0.27
     padded
    -0.27
     mir
    -0.25
    ç¬ĥ
    -0.24
    PropertyDescriptor
    -0.24
    life
    -0.24
    imed
    -0.24
    POSITIVE LOGITS
     those
    0.41
    those
    0.35
     Those
    0.35
    个ä½ĵ
    0.33
     quel
    0.32
    Those
    0.31
    éĤ£ä¸Ģ
    0.31
    sbin
    0.29
     quelle
    0.29
    éĤ£äºĽ
    0.29
    Activations Density 0.002%

    No Known Activations