© 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. 30096
    Prev
    Next
    INDEX
    Explanations

    varied document excerpts

    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
    owering
    -0.27
     edm
    -0.25
    èijµ
    -0.24
     Favor
    -0.24
    çĽ¯
    -0.24
     Approval
    -0.23
    èļĵ
    -0.23
    ä»Ģä¹Īåı«
    -0.23
     ctrl
    -0.23
    çħĬ
    -0.23
    POSITIVE LOGITS
    对该
    0.27
    å·
    0.26
     Manit
    0.26
    æ³Ħæ¼ı
    0.24
    ysts
    0.23
    oland
    0.23
    iloc
    0.23
    _commit
    0.23
    .pb
    0.23
    oit
    0.23
    Activations Density 2.154%

    No Known Activations