© 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. 109564
    Prev
    Next
    INDEX
    Explanations

    Some kind of text

    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
     ostensibly
    -0.27
    éŨæĪ·ç½ijç«Ļ
    -0.27
     suited
    -0.26
     wary
    -0.25
    æŃ·
    -0.24
     reminiscent
    -0.24
     obliged
    -0.24
    iguous
    -0.24
    åİĨæŶ
    -0.24
    åħģ
    -0.23
    POSITIVE LOGITS
    oyo
    0.27
    åĨįéĢł
    0.25
    noc
    0.25
    ä¸įéĢļ
    0.25
    YC
    0.25
    rut
    0.24
     proper
    0.24
    ghi
    0.24
    ä½łä¹Ł
    0.24
     **
    0.24
    Activations Density 0.958%

    No Known Activations