© 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. 30111
    Prev
    Next
    INDEX
    Explanations

    *

    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
    åıijçĶŁ
    -0.34
    çļĦåıijçĶŁ
    -0.29
    ä¼ļåıijçĶŁ
    -0.29
     occurring
    -0.28
     occurrence
    -0.28
     ocur
    -0.28
    eut
    -0.27
     occurrences
    -0.27
     occur
    -0.26
     Occ
    -0.25
    POSITIVE LOGITS
    overe
    0.27
    对ä¸įèµ·
    0.26
    arer
    0.26
    çĥĥ
    0.25
    edException
    0.25
    穷人
    0.25
    å¿Ĺ强
    0.25
    edral
    0.25
    åIJ¬äºĨ
    0.25
    oling
    0.24
    Activations Density 0.352%

    No Known Activations