© 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. 9-TRANSCODER-HP
    7. 29123
    Prev
    Next
    INDEX
    Explanations

    hollow / walls / tubes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     scores
    -0.27
    ouble
    -0.27
    blood
    -0.27
     blood
    -0.27
    çĶļèĩ³è¿ĺ
    -0.26
    串
    -0.26
    Jar
    -0.26
     ëĦĺ
    -0.25
     bore
    -0.25
    tar
    -0.25
    POSITIVE LOGITS
     Typeface
    0.28
    ertos
    0.25
    ansa
    0.25
    æłŁ
    0.25
    yses
    0.24
    åĵĤ
    0.24
    byss
    0.24
     Cursors
    0.23
    rics
    0.23
    ãĥijãĤ¿ãĥ¼ãĥ³
    0.23
    Activations Density 0.954%

    No Known Activations