© 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. 30-TRANSCODER-HP
    7. 97078
    Prev
    Next
    INDEX
    Explanations

    7

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĿ¢çĽ®
    -0.28
    ãģ§ãģįãģŁ
    -0.26
    å°Ĩ以
    -0.25
    able
    -0.25
    åĵ²
    -0.25
    è¶Ĭ好
    -0.24
    åıĹä¸įäºĨ
    -0.24
    ãģ§ãģįãĤĭ
    -0.24
     commons
    -0.23
    ëį°
    -0.23
    POSITIVE LOGITS
    æķ²
    0.26
    çħ®
    0.26
     subsid
    0.25
    å¤ļå¤ļ
    0.25
     tote
    0.24
     substant
    0.24
    unte
    0.24
     Nack
    0.24
     inhab
    0.24
     rehe
    0.24
    Activations Density 0.940%

    No Known Activations