© 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. 29481
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¹³åİŁ
    -0.26
    andex
    -0.26
    èģĶ
    -0.26
     Saves
    -0.25
    åį°èĬ±
    -0.25
    ersion
    -0.25
     Presidents
    -0.24
    仲
    -0.24
    SAVE
    -0.24
    èģĶåIJĪ
    -0.24
    POSITIVE LOGITS
    è¿ģ移
    0.29
    éĿ¢çĽ®
    0.28
    IBC
    0.28
    ioni
    0.28
    åĺ¹
    0.27
    å²Ĺ
    0.27
    èµ·æĿ¥äºĨ
    0.26
    edy
    0.25
    Ñĩе
    0.25
    SupportedContent
    0.25
    Activations Density 2.193%

    No Known Activations