© 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. 24-TRANSCODER-HP
    7. 149748
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ren
    -0.27
     sup
    -0.26
    -ended
    -0.25
    çħĮ
    -0.25
    vens
    -0.24
     histograms
    -0.23
     delay
    -0.23
    -choice
    -0.23
    angers
    -0.23
    erah
    -0.23
    POSITIVE LOGITS
     tread
    0.28
    Lot
    0.27
    ä»Ģä¹Īéĥ½
    0.27
    çļĦåĬ¨åĬĽ
    0.26
    åŁºæķ°
    0.26
    itness
    0.25
    æľ¬èº«çļĦ
    0.25
    ç¦ģ
    0.25
    Visitor
    0.25
    驾
    0.24
    Activations Density 0.038%

    No Known Activations