© 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. 29245
    Prev
    Next
    INDEX
    Explanations

    physics

    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
     NL
    -0.28
    tip
    -0.27
     Mic
    -0.26
    大å¥ĸ
    -0.26
    istik
    -0.26
     attract
    -0.26
    ilion
    -0.26
    ursor
    -0.26
    NL
    -0.25
    -tip
    -0.25
    POSITIVE LOGITS
    sections
    0.26
    骨
    0.26
    usher
    0.26
    èŁĨ
    0.25
    éĹ´éļĶ
    0.25
    .fe
    0.25
     mel
    0.25
    主æµģ
    0.25
    çĶ»
    0.24
    çªģåĩºéĹ®é¢ĺ
    0.24
    Activations Density 0.598%

    No Known Activations