© 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. 29257
    Prev
    Next
    INDEX
    Explanations

    cats

    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
    yer
    -0.29
    itches
    -0.27
    妨ç¢į
    -0.25
    åİ¥
    -0.25
    itas
    -0.25
    umas
    -0.25
     desn
    -0.24
    nas
    -0.24
    次è¦ģ
    -0.24
    by
    -0.24
    POSITIVE LOGITS
    inem
    0.28
    çĭŀ
    0.27
     Heard
    0.27
    remely
    0.25
    ä¸Ģè¾ĪåŃIJ
    0.24
    ipur
    0.24
    igne
    0.24
    æĹłæīĢ
    0.24
    nty
    0.24
     liner
    0.24
    Activations Density 5.631%

    No Known Activations