© 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. 18748
    Prev
    Next
    INDEX
    Explanations

    head

    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
    ythe
    -0.26
    Ĥæķ°
    -0.26
     Himself
    -0.25
     spark
    -0.25
     euler
    -0.24
    æ³ķå®Ŀ
    -0.24
     kole
    -0.24
    StackSize
    -0.24
    ambda
    -0.24
    å¾Ĺå¾Ī好
    -0.24
    POSITIVE LOGITS
     up
    0.51
    .up
    0.47
    up
    0.46
    -up
    0.45
    _up
    0.38
    -Up
    0.38
    	up
    0.36
    âĨij
    0.35
     Up
    0.35
    (up
    0.34
    Activations Density 0.854%

    No Known Activations