© 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. 41605
    Prev
    Next
    INDEX
    Explanations

    research studies

    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¶Ĭå¤ļ
    -0.29
    å¢ŀ
    -0.29
    ç¡®åĪĩ
    -0.28
    olec
    -0.27
    åĵªç§į
    -0.27
    atts
    -0.26
     mal
    -0.25
    slice
    -0.25
    åħ³èĬĤ
    -0.25
    åįĩé«ĺ
    -0.24
    POSITIVE LOGITS
    æĪĺçķ¥æĢ§
    0.29
    abo
    0.29
     priorities
    0.29
    ansom
    0.26
    coma
    0.26
    strategy
    0.26
    _interest
    0.25
    ocomplete
    0.25
     Nacht
    0.25
    bg
    0.25
    Activations Density 0.111%

    No Known Activations