© 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. 29480
    Prev
    Next
    INDEX
    Explanations

    flag

    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
    inject
    -0.28
     inject
    -0.26
    笾
    -0.26
    åºĶæľīçļĦ
    -0.25
    inge
    -0.25
    Needed
    -0.24
    éĤĢ请
    -0.24
    æĺ¯åIJ¦åŃĺåľ¨
    -0.24
    /assert
    -0.24
    avn
    -0.24
    POSITIVE LOGITS
     Herc
    0.28
     Weg
    0.26
    burgh
    0.26
    imizer
    0.26
    enk
    0.26
     child
    0.25
     kre
    0.24
     costs
    0.24
    gend
    0.23
    lac
    0.23
    Activations Density 0.805%

    No Known Activations