© 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. 25-TRANSCODER-HP
    7. 107238
    Prev
    Next
    INDEX
    Explanations

    money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minim
    -0.30
    achten
    -0.29
    utan
    -0.26
    urple
    -0.26
    ÑĥÑĤ
    -0.26
    è¶Ĭ大
    -0.25
    éĻĪåĪĹ
    -0.25
    æľĢå°ı
    -0.24
    ت
    -0.24
    äºĶ个
    -0.24
    POSITIVE LOGITS
    orney
    0.28
     bek
    0.27
     Deliver
    0.26
    æµģåIJij
    0.25
     deliveries
    0.24
    osoph
    0.24
    éģĬ
    0.24
    .si
    0.24
     circulating
    0.24
     devoted
    0.24
    Activations Density 0.916%

    No Known Activations