© 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. 22-TRANSCODER-HP
    7. 130944
    Prev
    Next
    INDEX
    Explanations

    reproduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨħ
    -0.29
    åħ·
    -0.28
    orious
    -0.28
    owed
    -0.27
    çĦ¶æĺ¯
    -0.27
    tron
    -0.26
    ä¸į该
    -0.26
    arp
    -0.25
    Æ°á»Łng
    -0.25
    jerne
    -0.24
    POSITIVE LOGITS
    ea
    0.27
    ece
    0.24
     concurrently
    0.24
    _elems
    0.24
    e
    0.24
    /generated
    0.24
    eated
    0.23
    éķ¦
    0.23
    .between
    0.23
     acquaintance
    0.23
    Activations Density 0.438%

    No Known Activations