© 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. 58619
    Prev
    Next
    INDEX
    Explanations

    any

    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
    éĤ£åıª
    -0.30
    ä¸Ģç¢Ĺ
    -0.30
    æľīå¤ļå°ij
    -0.29
    lobals
    -0.27
    éĤ£ä½į
    -0.26
    _CONTINUE
    -0.26
    訾
    -0.25
     MANY
    -0.25
    olarity
    -0.25
    evice
    -0.25
    POSITIVE LOGITS
    Actual
    0.28
     actual
    0.28
     effort
    0.28
     doubt
    0.27
    actual
    0.26
     activity
    0.26
    way
    0.25
     indication
    0.25
    ahrung
    0.25
     understanding
    0.24
    Activations Density 0.075%

    No Known Activations