© 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. 140929
    Prev
    Next
    INDEX
    Explanations

    Question words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    viron
    -0.32
    agram
    -0.26
     calmly
    -0.24
    ãģĤãĤĭ
    -0.24
    пи
    -0.24
    çģ«æĺŁ
    -0.23
     patiently
    -0.23
     Orb
    -0.23
     arresting
    -0.23
    ulent
    -0.23
    POSITIVE LOGITS
    åıĸå¾ĹäºĨ
    0.30
     COPYING
    0.25
    åıĸå¾Ĺ
    0.25
    åĬłæĮģ
    0.25
    产ä¸ļéĽĨèģļ
    0.24
    drs
    0.24
    æī¾åĪ°äºĨ
    0.24
     blessing
    0.24
     slack
    0.24
    æĿµ
    0.24
    Activations Density 7.430%

    No Known Activations