© 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. 33-TRANSCODER-HP
    7. 52853
    Prev
    Next
    INDEX
    Explanations

    ap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACLE
    -0.28
    acebook
    -0.27
     RTC
    -0.27
    me
    -0.25
    orca
    -0.25
    æĤ²è§Ĥ
    -0.25
     Barrel
    -0.25
    ATAR
    -0.24
    çĦĺ
    -0.24
    .SQLite
    -0.24
    POSITIVE LOGITS
    æķ´
    0.29
    æµ®
    0.28
     rin
    0.27
    trand
    0.27
    ç®Ģ
    0.27
    åĴĮ社ä¼ļ
    0.27
    edException
    0.26
    oren
    0.26
    inan
    0.26
     imp
    0.26
    Activations Density 0.004%

    No Known Activations