© 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. 109390
    Prev
    Next
    INDEX
    Explanations

    Code and license agreements

    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
    Negative Logits
    ä¸įæĿ¥
    -0.28
    luet
    -0.27
    uki
    -0.27
     Mines
    -0.26
    responses
    -0.25
    деÑĤ
    -0.25
    åħ¥å¢ĥ
    -0.25
    деж
    -0.25
     chests
    -0.25
    oes
    -0.25
    POSITIVE LOGITS
    éĹª
    0.30
     alone
    0.28
    {text
    0.26
    æ§
    0.24
    åģļçļĦäºĭ
    0.24
    缴è§Ĥ
    0.24
    ä¹į
    0.24
    æ²±
    0.24
    alone
    0.23
    istory
    0.23
    Activations Density 0.008%

    No Known Activations