© 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. 58576
    Prev
    Next
    INDEX
    Explanations

    house

    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
    éĢģä¸Ĭ
    -0.25
    NESS
    -0.25
    éĻĦå±ŀ
    -0.25
    unker
    -0.24
    åķĨæĬ¥
    -0.24
     housed
    -0.24
    í
    -0.24
    itage
    -0.24
    å£ij
    -0.23
     superclass
    -0.23
    POSITIVE LOGITS
     fetching
    0.30
    eno
    0.30
     Fior
    0.28
     roses
    0.26
    -season
    0.26
    retrieve
    0.25
     Scene
    0.25
    aidu
    0.25
    ÑĥÑģÑĤ
    0.24
    çİ«çij°
    0.24
    Activations Density 0.011%

    No Known Activations