© 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. 30-TRANSCODER-HP
    7. 95231
    Prev
    Next
    INDEX
    Explanations

    Mah

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     begs
    -0.30
     Qualified
    -0.28
    bury
    -0.28
     qualified
    -0.27
     intention
    -0.26
    åŃ¦ä¹ł
    -0.26
    æ²Ļ
    -0.25
    .comp
    -0.25
    pong
    -0.25
     swept
    -0.25
    POSITIVE LOGITS
    ç½ij讯
    0.31
     moden
    0.26
     LOVE
    0.26
    ittal
    0.25
     Lover
    0.25
    ocratic
    0.24
    æĶ¾æīĭ
    0.24
    uh
    0.24
     resized
    0.24
    çĪ±
    0.23
    Activations Density 0.883%

    No Known Activations