© 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. 111237
    Prev
    Next
    INDEX
    Explanations

    with

    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
     MSNBC
    -0.27
    lich
    -0.26
     baj
    -0.25
     лиÑĨа
    -0.25
     sincer
    -0.24
     HEIGHT
    -0.24
    APTER
    -0.24
     ÐłÐ¾ÑģÑģий
    -0.24
    .accuracy
    -0.23
    _physical
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
     cardinal
    0.27
    zion
    0.26
     machine
    0.25
    驶
    0.25
    succ
    0.25
     tooltip
    0.25
     wheelchair
    0.25
    -badge
    0.25
    .tem
    0.24
    Activations Density 0.013%

    No Known Activations