© 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. 31-TRANSCODER-HP
    7. 18135
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ize

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embedded
    -0.28
    =_("
    -0.27
     predetermined
    -0.26
    embedded
    -0.25
    æĪijåı¯ä»¥
    -0.25
     constrained
    -0.25
     customized
    -0.25
     assigned
    -0.24
     built
    -0.24
    Embedded
    -0.24
    POSITIVE LOGITS
     organize
    0.45
    etrize
    0.42
     expand
    0.39
     summarize
    0.39
     characterize
    0.38
     settle
    0.38
     encode
    0.38
     organise
    0.38
     execute
    0.37
    normalize
    0.37
    Activations Density 22.638%

    No Known Activations