© 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. 41619
    Prev
    Next
    INDEX
    Explanations

    learn

    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
    Negative Logits
    è§ĨåIJ¬
    -0.30
    ide
    -0.27
     EDT
    -0.27
    æİ¢éĻ©
    -0.27
    esium
    -0.26
    еÑī
    -0.25
    egl
    -0.25
    åįĹæŀģ
    -0.25
     '.')
    -0.25
     Initially
    -0.24
    POSITIVE LOGITS
    SAMPLE
    0.29
     CONS
    0.28
    AUTO
    0.27
    人æīįéĺŁä¼į
    0.27
    èĪĮ头
    0.27
     crowned
    0.26
    èĩªè§ī
    0.26
    izer
    0.26
     killing
    0.25
     giÃłu
    0.25
    Activations Density 0.263%

    No Known Activations