© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23859
    Prev
    Next
    INDEX
    Explanations

    Weddings and funerals

    np_max-act · gemini-2.0-flash
    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
    èĢ³è¾¹
    -0.27
    Independ
    -0.27
    itionally
    -0.26
    uario
    -0.25
    [SerializeField
    -0.24
     postpon
    -0.24
     CASCADE
    -0.24
    纪å§Ķ
    -0.24
    커
    -0.23
    apel
    -0.23
    POSITIVE LOGITS
     gst
    0.27
     /↵↵
    0.26
    мÑĥ
    0.26
    é¼ĵ
    0.25
    elts
    0.25
    ime
    0.25
    ueblo
    0.25
    SubMenu
    0.24
    hid
    0.24
    æ°´ä¸Ĭ
    0.24
    Activations Density 0.002%

    No Known Activations