© 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. 107116
    Prev
    Next
    INDEX
    Explanations

    first

    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
     Continued
    -0.26
    ë§ī
    -0.25
    Continue
    -0.25
    å°º
    -0.24
     Continuing
    -0.24
    æĸ°
    -0.24
    åħ¶ä¸Ńæľī
    -0.24
    PRIMARY
    -0.24
     æİ
    -0.24
     Calories
    -0.24
    POSITIVE LOGITS
    åºĶåıĬæŶ
    0.27
    æķĸ
    0.26
    å¼Ģåıij建设
    0.25
    onné
    0.25
    éĩĩåıĸ
    0.25
    ago
    0.25
    éĻħ
    0.25
    _PO
    0.25
    çŃ¹èµĦ
    0.24
     tackled
    0.24
    Activations Density 0.183%

    No Known Activations