© 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. 19524
    Prev
    Next
    INDEX
    Explanations

    prop

    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
    æķıæĦŁ
    -0.30
    fin
    -0.29
     sensitive
    -0.26
    æĸĩåѦ
    -0.26
    .AutoScale
    -0.26
    ä¸Ģå®ļèĥ½
    -0.25
    reek
    -0.25
     risking
    -0.25
     sensitivity
    -0.24
    è¶ħé¢Ŀ
    -0.24
    POSITIVE LOGITS
     prop
    0.58
    prop
    0.52
    (prop
    0.49
    .prop
    0.48
     Prop
    0.48
    Prop
    0.43
    _prop
    0.43
    	prop
    0.42
    props
    0.39
     props
    0.38
    Activations Density 5.100%

    No Known Activations