© 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. 23599
    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
    PageIndex
    -0.28
    æĸ¹å¼ı
    -0.26
    ohn
    -0.26
     comfort
    -0.26
    anni
    -0.26
    andbox
    -0.26
    NC
    -0.25
     reass
    -0.25
    èĦļä¸ĭ
    -0.24
    ç¬ĭ
    -0.24
    POSITIVE LOGITS
    chod
    0.30
    æĢ»ä¼ļ
    0.26
    strt
    0.25
    ardy
    0.25
    ALSE
    0.25
    alen
    0.25
     registered
    0.25
     methyl
    0.25
    elper
    0.25
    æĬµè¾¾
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.