© 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. 18333
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     alteration
    -0.25
    cks
    -0.25
    _RDWR
    -0.24
    åij½åIJį
    -0.24
    å¾Īç®Ģåįķ
    -0.24
    æݢ访
    -0.24
    -ton
    -0.24
    ober
    -0.24
     sniff
    -0.23
    大å°ı
    -0.23
    POSITIVE LOGITS
    iphone
    0.28
    bra
    0.28
    abet
    0.27
    auté
    0.27
    èĬĴ
    0.26
     puesto
    0.25
     Monter
    0.25
    ITAL
    0.25
    /cop
    0.25
    ITA
    0.24
    Activations Density 0.790%

    No Known Activations

    This feature has no known activations.