© 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. 27-TRANSCODER-HP
    7. 58540
    Prev
    Next
    INDEX
    Explanations

    choices and possibilities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ë§Įíģ¼
    -0.35
    è¿Ļä¹Ī
    -0.33
    éĤ£ä¹Īå¤ļ
    -0.32
    è¿Ļä¹Īå¤ļ
    -0.30
    udded
    -0.30
    äºĨå¤ļå°ij
    -0.29
    æľīå¤ļå°ij
    -0.28
    éĤ£éº¼
    -0.28
    éĢĻ麼
    -0.28
    iÅŁ
    -0.27
    POSITIVE LOGITS
    liest
    0.30
    .inc
    0.29
    æį
    0.27
     signific
    0.27
    oral
    0.26
     familiar
    0.25
    mas
    0.24
    å±Ĭ
    0.24
    æĦŁ
    0.24
     Brut
    0.24
    Activations Density 0.006%

    No Known Activations