© 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. 58459
    Prev
    Next
    INDEX
    Explanations

    Medical cases, "endocrine," "tumors"

    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
    æķ´é¡¿
    -0.28
    çĻĸ
    -0.27
    è°ª
    -0.26
     кÑĢÑĭÑĪ
    -0.26
     drafts
    -0.26
     defeats
    -0.26
    rid
    -0.26
    _connections
    -0.25
    Draft
    -0.24
    俦
    -0.24
    POSITIVE LOGITS
    åĸĦ
    0.30
    avor
    0.28
    ior
    0.28
    utivo
    0.27
    说äºĨ
    0.27
     Deposit
    0.26
    outer
    0.26
     Romans
    0.26
    ·æĸ°
    0.26
    ORIGINAL
    0.25
    Activations Density 0.017%

    No Known Activations