© 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. 12-TRANSCODER-HP
    7. 22472
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTO
    -0.26
    åĮħ容
    -0.25
    OLS
    -0.25
     Staten
    -0.25
    Compatible
    -0.25
    è¢Ń
    -0.24
     obras
    -0.24
    ç®ķ
    -0.24
    (Arg
    -0.24
    reck
    -0.23
    POSITIVE LOGITS
    åİĤ
    0.27
    enh
    0.27
     withdrawn
    0.27
    女è£ħ
    0.26
    èݺ
    0.26
    oldt
    0.25
     machines
    0.25
    WSC
    0.25
    æįŀ
    0.25
     sadd
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.