© 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. 112802
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ä¸Ģåı£
    -0.27
    idders
    -0.27
    esser
    -0.26
    åĪº
    -0.26
    rase
    -0.26
    avra
    -0.25
    casts
    -0.25
    Ñĥз
    -0.24
    repr
    -0.24
    éĤµ
    -0.24
    POSITIVE LOGITS
     ago
    0.31
    -old
    0.29
     stuck
    0.28
    ç¶ļ
    0.28
     duration
    0.28
     Falcon
    0.28
     after
    0.27
     past
    0.27
     lag
    0.27
    æĮģç»Ń
    0.27
    Activations Density 0.152%

    No Known Activations