© 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. 32-TRANSCODER-HP
    7. 43989
    Prev
    Next
    INDEX
    Explanations

    Related to "space"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä»Ĺ
    -0.29
    insula
    -0.26
    markt
    -0.26
    éĹŃ
    -0.25
    èĮ¬
    -0.25
    edImage
    -0.24
     nast
    -0.24
    sess
    -0.24
    åijĹ
    -0.24
    idelberg
    -0.24
    POSITIVE LOGITS
    空
    0.74
    为空
    0.57
     spa
    0.52
    穸
    0.52
    spa
    0.51
     sap
    0.50
    -sp
    0.48
    ê³µ
    0.47
     spaced
    0.47
     Esp
    0.46
    Activations Density 0.002%

    No Known Activations