© 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. 14-TRANSCODER-HP
    7. 41450
    Prev
    Next
    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¯Ł
    -0.27
     ÑħаÑĢакÑĤеÑĢиÑģÑĤик
    -0.26
    xampp
    -0.26
    :variables
    -0.24
    PRI
    -0.24
    akest
    -0.23
    mund
    -0.23
    ساÙħ
    -0.23
     sounded
    -0.23
    æīįè¡Į
    -0.23
    POSITIVE LOGITS
    ä»ĸ们ä¼ļ
    0.29
    ä»ĸ们æĺ¯
    0.28
    afone
    0.28
    corn
    0.27
     tess
    0.25
    çĶµè§Ĩ
    0.25
     Há»į
    0.25
    esto
    0.24
    èįŀ
    0.24
    calcul
    0.24
    Activations Density 2.135%

    No Known Activations