© 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. 30120
    Prev
    Next
    INDEX
    Explanations

    Iraq

    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
    tracking
    -0.27
    trak
    -0.27
    è·Łè¸ª
    -0.25
    è¯Ĥ
    -0.25
    åįķ车
    -0.25
    .unlock
    -0.25
    WithTag
    -0.25
    ocols
    -0.24
     anders
    -0.24
    umer
    -0.24
    POSITIVE LOGITS
    常
    0.29
    otropic
    0.27
    rop
    0.25
     Essays
    0.25
    pe
    0.25
    .Unity
    0.25
     addresses
    0.24
     Address
    0.24
     pe
    0.24
    åľ°åĿĢ
    0.24
    Activations Density 1.566%

    No Known Activations