© 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. 107111
    Prev
    Next
    INDEX
    Explanations

    code and copyright notices

    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
    porter
    -0.27
    éĵ¶
    -0.25
    æĿİçĻ½
    -0.25
     Tok
    -0.25
    aise
    -0.25
    åĬ©æīĭ
    -0.25
     TOKEN
    -0.24
     displacement
    -0.24
    flation
    -0.24
    oken
    -0.24
    POSITIVE LOGITS
    arus
    0.28
    åľ¨éĤ£éĩĮ
    0.27
    azines
    0.27
     dine
    0.26
    ús
    0.25
    è¯ķ
    0.25
    OUSE
    0.25
    ografia
    0.25
    ografÃŃa
    0.25
    éĤ£éĩĮ
    0.25
    Activations Density 0.105%

    No Known Activations