© 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. 20-TRANSCODER-HP
    7. 62664
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç§ī
    -0.29
    ingly
    -0.26
    è¾IJ
    -0.25
    é£Ł
    -0.25
    ñas
    -0.25
    éĩľ
    -0.24
    æ²®
    -0.24
    overe
    -0.24
    TED
    -0.24
    usterity
    -0.24
    POSITIVE LOGITS
    metis
    0.27
    RAP
    0.27
    .loop
    0.26
    Retention
    0.25
    _INITIALIZER
    0.25
     scenes
    0.25
    çł£
    0.24
    åĪĿãĤģãģ¦
    0.24
     Hardy
    0.24
    _roles
    0.24
    Activations Density 0.425%

    No Known Activations