© 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. 41676
    Prev
    Next
    INDEX
    Explanations

    conductor

    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
    踩
    -0.27
    ↵        ↵        ↵
    -0.26
     undef
    -0.25
    缣
    -0.25
     Kushner
    -0.24
    ãĤıãĤĮ
    -0.24
    æ¯į
    -0.24
    ales
    -0.24
    erule
    -0.24
    č↵        č↵
    -0.24
    POSITIVE LOGITS
    dating
    0.28
    NEY
    0.27
    iez
    0.27
    éķ¿èĢģ
    0.26
    оÑı
    0.25
    ilda
    0.25
    girls
    0.25
    since
    0.25
    `\
    0.25
    æĢ¦
    0.24
    Activations Density 0.793%

    No Known Activations